inputs stringlengths 38 313k | targets stringlengths 0 4.86k | _template_idx int64 0 9 | _task_source stringclasses 1 value | _task_name stringlengths 19 85 | _template_type stringclasses 2 values | embedding listlengths 1.02k 1.02k |
|---|---|---|---|---|---|---|
You need to create a question containing a blank (_), based on the given context word. Your question must contain two persons --PersonX and PersonY. The expected answer to your question must be PersonX. PersonX and PersonY should not be equally likely to fill the blank. There should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your question. Avoid repeating the same style, pattern, or phrases in each question, try to increase diversity by varying sentence structure, blank placement, etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Person X and Person Y have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.
[Q]: Context Word: glow.
[A]: Because PersonX was running down the street towards PersonY, it was _ who felt hot and had a rosy glow on her cheeks.
[Q]: Context Word: movies.
[A]: PersonX always paid for PersonY's tickets to the movies because _ always had plenty of money.
[Q]: Context Word: sink.
[A]: | PersonX asked PersonY to clean the bathroom sink for her, because _ had forgotten to do it.
| 5 | NIv2 | task032_winogrande_question_generation_person | fs_opt | [
0.2939663529396057,
0.6750720143318176,
0.03208800405263901,
-0.06463800370693207,
-0.06936503201723099,
-0.6378141641616821,
0.7387489080429077,
0.6404718160629272,
-0.12561288475990295,
-0.8510133624076843,
0.2519930899143219,
0.11460036039352417,
-0.5996778011322021,
0.25603964924812317... |
Teacher:Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
Teacher: Now, understand the problem? Solve this instance: ['[Music]', "we're", 'in', 'the', 'fut', 'influence', 'looking', 'at', 'a', 'large', 'baroque', 'painting', 'by', 'the', 'artist', 'Artemisia', 'Gentileschi', 'this', 'is', 'the', 'painting', "that's", 'most', 'often', 'reproduced', 'by', 'Artemisia', 'the', 'subject', 'is', 'Judith', 'and', 'Holofernes', 'this', 'is', 'a', 'biblical', 'subject', 'Old', 'Testament', 'and', "it's", 'the', 'story', 'of', 'a', 'heroic', 'woman', 'and', 'of', 'course', 'that', 'is', 'always', 'a', 'handy', 'thing', 'when', 'you', 'heard', 'art', 'historian', 'and', "you're", 'talking', 'about', 'a', 'woman', 'artist', 'in', 'fact', "it's", 'difficult', 'often', 'with', 'women', 'artists', 'not', 'to', 'read', 'their', 'biography', 'into', 'the', 'paintings', 'but', "let's", 'just', 'take', 'a', 'close', 'look', 'at', 'the', 'painting', 'to', 'start', 'with', 'it', 'is']
Student: | ['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'UNKNOWN_TYPE_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF'] | 6 | NIv2 | task1416_youtube_caption_corrections_incorrect_grammar_classification | zs_opt | [
0.3630977272987366,
0.34840327501296997,
-0.2577421963214874,
0.025079451501369476,
0.18133382499217987,
-0.5464299917221069,
0.2871782183647156,
0.6596113443374634,
0.16413584351539612,
0.3252701759338379,
-0.04343297332525253,
0.1515830159187317,
-0.3023013770580292,
-0.31889328360557556... |
You will be given a definition of a task first, then some input of the task.
In this task, you are given an input list A comprising of numbers and alphabets. You need to extract and sort the unique alphabets in the list. The alphabets in the input list will only be in lowercase. Return -1 if there is no alphabet in the input list.
['3347', '7827', 'u', '1363', '711', '8247', '9187', '2783', '2485', '5759', 'k']
Output: | k, u | 1 | NIv2 | task636_extract_and_sort_unique_alphabets_in_a_list | zs_opt | [
-0.502979040145874,
0.42444589734077454,
-0.35219472646713257,
-0.0438314825296402,
0.5240011215209961,
0.4462953507900238,
0.9981957077980042,
0.2439097762107849,
-0.2893699109554291,
0.23046211898326874,
-0.3075522780418396,
-0.4128091335296631,
0.17824557423591614,
-0.17644278705120087,... |
Definition: A text is given in Bengali. Translate it from the Bengali language to the Telugu language. The translation must not omit or add information to the original sentence.
Input: ఈ మూడు రంగాల లోను ఉమ్మడి ప్రయోజనాలను పొందేందుకు గాను భారతదేశం మరియు డెన్మార్క్ ల మధ్య సహకారాన్ని ప్రోత్సహించడం, అభివృద్ధి చేయడంతో పాటు సమన్వయాన్ని ఏర్పరచడం కూడా ఈ ఒప్పందం యొక్క ధ్యేయం.
Output: | সমঝোতার মূল উদ্দেশ্য হল দুটি দেশের মধ্যে বিজ্ঞান, প্রযুক্তি ও উদ্ভাবনের বিভিন্ন ক্ষেত্রে সহযোগিতার বাতাবরণ গড়ে তোলা। | 2 | NIv2 | task1032_pib_translation_telugu_bengali | zs_opt | [
-0.3741165101528168,
0.7245398759841919,
0.18690206110477448,
-0.26124075055122375,
0.2338353991508484,
0.33088189363479614,
-0.015266289003193378,
0.08447737246751785,
-0.31190764904022217,
-0.24841347336769104,
-0.5627156496047974,
0.2180083990097046,
-0.019394421949982643,
0.30371046066... |
Detailed Instructions: You are given a sentence in Italian. Your job is to translate the Italian sentence into Hebrew.
Q: I suoi compiti chiave sono due.
A: | ויש שני דברים מרכזיים שהיא צריכה לעשות. | 9 | NIv2 | task1251_ted_translation_it_he | zs_opt | [
-0.4191156327724457,
0.34278810024261475,
-0.10339478403329849,
-0.24692752957344055,
-0.35461923480033875,
0.42543351650238037,
0.026621565222740173,
0.1980283409357071,
0.3616923391819,
-0.2674698233604431,
-0.06706927716732025,
-0.5431889891624451,
-0.8876171708106995,
0.353531718254089... |
In this task, you are given one English sentence. The major part of the sentences talk about health-related topics, but some of the them describe an organization and its activities. Your job is to translate the given sentences into Swedish.
Q: We can offer the opportunity of being an important part of a fast growing European Agency.
A: | Vi erbjuder våra anställda möjligheten att vara en viktig del i ett snabbt växande EU-organ. | 4 | NIv2 | task1395_europa_ecdc_tm_en_sv_translation | zs_opt | [
0.14793531596660614,
1.2112993001937866,
0.3232865631580353,
-0.6562266945838928,
-0.2194964736700058,
-0.5574556589126587,
0.42651471495628357,
0.6527680158615112,
0.3972388207912445,
0.2390364110469818,
0.34974586963653564,
0.3136900067329407,
-0.6531965732574463,
0.029284821823239326,
... |
In this task, you are given two strings A,B. Find the longer of the two lists, convert it to lowercase, and return all the unique alphabets used in it. The two input strings are never equal.
Q: BErUlxsfsCZsoUyCXERc, KxfsCZsoUyCXPbuGGgdVU
A: b, c, d, f, g, k, o, p, s, u, v, x, y, z
****
Q: HZOAWycLEpA, cfwiAWyctY
A: a, c, e, h, l, o, p, w, y, z
****
Q: nmslkKGxgzpnUVBJwmF, FjTueMlkKGxgzpnUWTEel
A: | e, f, g, j, k, l, m, n, p, t, u, w, x, z
****
| 4 | NIv2 | task756_find_longert_substring_and_return_all_unique_alphabets_in_it | fs_opt | [
-0.3037906587123871,
1.2245383262634277,
-0.12737637758255005,
-0.5729681253433228,
0.35641342401504517,
-0.021969718858599663,
0.9686250686645508,
0.07962900400161743,
0.18510688841342926,
-0.2265930026769638,
-0.7040203213691711,
-0.10672850906848907,
0.06070123612880707,
-0.229920104146... |
Teacher:Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.
Teacher: Now, understand the problem? Solve this instance: 5:38:19 occurs between 03:39:22 and 05:47:36
Student: | True | 6 | NIv2 | task1507_boolean_temporal_reasoning | zs_opt | [
0.2027834802865982,
0.06862424314022064,
-0.4893829822540283,
0.441956102848053,
-0.3849523067474365,
-0.34290745854377747,
-0.22580859065055847,
0.9778534770011902,
-0.38626426458358765,
-0.2222193330526352,
-0.5778796672821045,
-0.5557273626327515,
-0.16651219129562378,
-0.45188307762145... |
Detailed Instructions: In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether it is plausible for the Head to desire the Tail or not. In this task, desire means desires of sentient entities. For example, doctors likely desire to cure a patient. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Problem:Head: person<sep>Tail: smooth sailing
Solution: | Yes | 8 | NIv2 | task1213_atomic_classification_desires | zs_opt | [
-0.0172728281468153,
0.30663540959358215,
0.19111768901348114,
-0.590141236782074,
-0.29096823930740356,
-0.8055230975151062,
0.9828258752822876,
0.11876368522644043,
-0.6043806672096252,
-0.27265453338623047,
0.2293282300233841,
-0.48846691846847534,
-0.31927967071533203,
0.07064665108919... |
instruction:
In this task, you are given an impractical statement. You are also given three reasons (associated with "A", "B", "C") explaining why this statement doesn't make sense. You must choose the most corresponding reason explaining why this statement doesn't make sense.
question:
He rakes leaves in his backyard in the spring.
(A) Spring is the season when leaves start to grow.
(B)Autumn is the season when leaves fall from trees.
(C)Autumn is the season when leaves turn brown.
answer:
B
question:
The weather is so hot that it began to snow.
(A) Snow is usually white, and grass is usually green.
(B)The heat would melt the snow.
(C)The snow did not arrive on time.
answer:
B
question:
She cooked a library on the grill.
(A) A library is a building, not something you cook.
(B)The library was out of books on how to cook with a grill.
(C)The grill already being used to cook somebody else's library.
answer:
| A
| 9 | NIv2 | task295_semeval_2020_task4_commonsense_reasoning | fs_opt | [
-0.020271770656108856,
0.3643568754196167,
-0.9152581691741943,
-0.5578071475028992,
-0.551263689994812,
-1.4068872928619385,
0.3186553120613098,
0.37933671474456787,
-0.3887825310230255,
-0.25940924882888794,
-0.36191326379776,
0.4885266125202179,
-0.784408450126648,
0.18413038551807404,
... |
Given the task definition and input, reply with output. In this task, you are given a sentence in Persian, and your task is to translate it into English.
دوشنبه صبحها تنها کاري که ميکردم اين بود که به هفته آينده فکر کنم .
| monday mornings , i just thought about next week . | 5 | NIv2 | task659_tep_fa_en_translation | zs_opt | [
-1.3389477729797363,
0.9760510325431824,
0.21028344333171844,
-0.10950200259685516,
-0.9259614944458008,
0.37590405344963074,
0.5245380997657776,
0.2924586534500122,
0.46473535895347595,
-0.42926108837127686,
-0.6051568388938904,
0.6113580465316772,
-0.5007345676422119,
0.30421823263168335... |
Instructions: We would like you to assess the QUALITY of each of the following argument (discussing Gun Control) and determine if the argument is Valid or Invalid. A valid argument is clearly interpretable and either expresses an argument, or a premise or a conclusion that can be used in an argument for the topic of gun control. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of gun control.
Input: People that read the 2nd amend as a militia thing also must think dangerous criminals will obey gun control laws.
Output: | Valid | 3 | NIv2 | task150_afs_argument_quality_gun_control | zs_opt | [
-0.015689508989453316,
0.805777370929718,
0.4939154088497162,
-0.5595428943634033,
-0.4841119647026062,
-1.885114312171936,
0.47768434882164,
0.30153876543045044,
0.43636441230773926,
0.09957525134086609,
-0.8620247840881348,
-0.6803282499313354,
-0.4592819809913635,
0.17595651745796204,
... |
Definition: This task is about translating a given English language sentence to Spanish.
Input: Well, that's a pretty good lesson for anybody, no matter what you choose to do in your life.
Output: | Bueno, eso es una muy buena lección a nadie, no importa lo que optar por hacer en su vida. | 2 | NIv2 | task1691_qed_amara_translation | zs_opt | [
-0.1629103273153305,
0.3675748407840729,
0.020776573568582535,
-0.26169779896736145,
-0.3716801404953003,
-0.9970458745956421,
0.636983335018158,
0.36388325691223145,
0.537039577960968,
-0.4735473692417145,
-0.4275973439216614,
0.02660181373357773,
-0.18164393305778503,
-0.0244063660502433... |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
Given a sentence and an entity, the task is to select the authors sentiment towards the enity. Sentiments can be Positive, Neutral and Negative. Select Positive if the sentence expresses a positive view towards the given entity or praises its quality or skills. Select Neutral if the sentence expresses no clear view towards the entity or has equal amounts of positive and negative statements or expressing some fact/quote by someone else. Select Negative if the sentence expresses a negative view towards like harsh remarks, criticizing entities action/decision etc. Note that URLs in the text have been replaced with [Link].
What is the sentiment of the following sentence towards the entity Bill Clinton ? Bill Clinton knows how to win friends and influence people.
Solution: Positive
Why? Here the author of the document praises Bill for this ability to win friends.
New input: What is the sentiment of the following document towards the entity Cristiano Ronaldo ? Soccer Football - Champions League - Borussia Dortmund vs Real Madrid - Westfalenstadion Dortmund Germany - September 26 2017 Real Madrid’s Cristiano Ronaldo celebrates scoring their third goal with Sergio Ramos and Luka Modric REUTERS/Leon Kuegeler
Solution: | Positive | 0 | NIv2 | task421_persent_sentence_sentiment_classification | fs_opt | [
-0.22911611199378967,
0.18818733096122742,
0.17931805551052094,
0.4663621187210083,
0.5122814774513245,
-0.4182303547859192,
0.5987734794616699,
0.322433739900589,
0.12046445161104202,
-0.022887464612722397,
-0.36838531494140625,
0.39473286271095276,
-0.293911874294281,
-0.2229948043823242... |
Teacher: You are given a sentence in Galician. Your job is to translate the Galician sentence into Italian.
Teacher: Now, understand the problem? If you are still confused, see the following example:
Isto inclúe un sistema en árabe chamado al-jebra.
Solution: Tra di esse, si annovera il piccolo sistema in arabo detto al-jebr.
Reason: The Galician sentence is correctly translated into Italian, because the meaning is preserved.
Now, solve this instance: Quero falarvos dunha amiga miña que ensinaba inglés para adultos en Abu Dhabi.
Student: | Voglio raccontarvi della mia amica che insegnava inglese agli adulti a Abu Dhabi. | 2 | NIv2 | task1243_ted_translation_gl_it | fs_opt | [
-0.4146343469619751,
0.920846700668335,
-0.2397061586380005,
-0.20086751878261566,
-0.4218902587890625,
-0.9107041358947754,
0.6515278816223145,
0.8229140639305115,
-1.0549404621124268,
0.16957660019397736,
0.04726759344339371,
-0.05704020336270332,
-0.825838565826416,
0.22153009474277496,... |
Detailed Instructions: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: identity-attack and non-identity-attack. Identity attack refers to anything rude or disrespectful about someone's identity, including appearance, race, gender, and sexual orientation.
Q: Comment: For every low end DACA brown, deport a black!
A: | Identity-attack | 9 | NIv2 | task325_jigsaw_classification_identity_attack | zs_opt | [
-0.46945732831954956,
0.14622390270233154,
0.40030747652053833,
0.4145481586456299,
-0.19196505844593048,
0.14404922723770142,
0.5933402180671692,
0.3227824866771698,
0.5528496503829956,
0.5785868167877197,
0.3063870072364807,
-0.04103463143110275,
-0.3358016908168793,
-0.5747253894805908,... |
Detailed Instructions: In this task, you are given a sentence in the English language and your task is to convert it into the Swedish language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).
Problem:Anyone, therefore, who invites Franz Fischler to his house to somehow account for the fact that his nationality is Austrian, should examine their own motives in the context of a debate, which has been necessarily shadowed by references to xenophobia and even more lethal evils in this world.
Solution: | Var och en som därför bjuder in Franz Fischler till sitt hem för att av någon anledning förklara det faktum att han är av österrikisk nationalitet bör granska sina egna motiv i samband med en debatt som nödvändigtvis har skymts av hänvisningar till främlingsfientlighet och även mer farlig ondska i denna värld. | 8 | NIv2 | task313_europarl_en_sv_translation | zs_opt | [
-0.05655577778816223,
0.1751784086227417,
0.06090434640645981,
-0.42400234937667847,
0.05405781418085098,
0.14970070123672485,
1.3829333782196045,
-0.09864184260368347,
0.26196420192718506,
0.41381633281707764,
-0.24619947373867035,
0.9684797525405884,
-1.2304843664169312,
-0.7366086840629... |
Detailed Instructions: You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Galician.
See one example below:
Problem: 処方箋を支払う為の保険は ？
Solution: Terán seguro para pagar a receita?
Explanation: The Japanese sentence is correctly translated into Galician, because the meaning is preserved.
Problem: 近年新たな技術の登場によって自然の本来の姿や自然界での出来事が少しずつ分かる様になってきました私たちが及ぼした影響も分かる様になりました
Solution: | As novas tecnoloxías estannos axudando a entender a natureza da natureza, a natureza do que está a suceder. Mostrándonos a nosa pegada na Terra. | 4 | NIv2 | task1095_ted_translation_ja_gl | fs_opt | [
-0.3668433725833893,
0.8732917308807373,
0.2731095254421234,
-0.9468168020248413,
-0.16157732903957367,
-1.1703611612319946,
0.38322147727012634,
1.059539556503296,
0.1304863691329956,
-0.01572313904762268,
-0.4432303309440613,
0.450958251953125,
-1.0574634075164795,
0.2925686538219452,
... |
Detailed Instructions: In this task, you're given a review from Amazon. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good.
Q: Almost half of these had opened so I spent an hour before service distinguishing which ones I had to throw away and which ones were still usable and then cleaning the sticky off of the usable ones.
A: | 1 | 9 | NIv2 | task1310_amazonreview_rating_classification | zs_opt | [
-0.00002070167101919651,
-0.4661233127117157,
-0.014717066660523415,
0.21712511777877808,
0.30225154757499695,
-0.2790907919406891,
0.5494296550750732,
0.36336901783943176,
-0.30993741750717163,
0.6754084825515747,
-0.47553014755249023,
0.10901256650686264,
-0.4095149040222168,
-0.20382635... |
Detailed Instructions: Given a sentence in the Japanese, provide an equivalent translation in Filipino that retains the same meaning through the translation. In translation, keep numbers as it is.
Q: ニューヨーク・タイムズの記事の匿名の情報源によると、機密文書2005年度法的見解は「これまでに中央情報局によって用いられた最も辛辣な尋問技術の拡大的裏書」という内容を含んでおり、頭の殴打、非常な低温、およびウォーターボーディングと呼ばれる水責めの手法がテロ容疑者に対し用いられることを明確に認可した。
A: | Ayon sa walang pangalang mga pinanggalingan, binanggit sa The New York Times na artikulo, ang bukud-bukod na 2005 opiniyong panglegal kasama "ang malawak na pagpapakilala sa pinakamabagsik na mga paraan ng pagsisiyasat na ginamit ng Central Intelligence Agency," at maliwanag na pinahintulutan ang paggamit ng mga taktika kasama ang paghampas sa ulo, sobrang lamig na temperatura, at sunud-sunod na paraan ng paglunod na kilala na waterboarding laban sa mga pinaghihinalaang mga terorista. | 9 | NIv2 | task1118_alt_ja_fil_translation | zs_opt | [
0.33274370431900024,
0.34725701808929443,
-0.2684937119483948,
-0.13598160445690155,
-0.0604034885764122,
-1.0901081562042236,
0.28218990564346313,
-0.07165809720754623,
-0.16954392194747925,
0.23544393479824066,
-0.3196422755718231,
-0.15970386564731598,
-1.0175926685333252,
0.43984311819... |
Definition: Given a pair of words, generate the relation between them. The first word is called the 'concept' and the second word is called the 'relatum' The relation must be one of the following: co-hyponym (coordinate), hypernym, meronym, attribute, event, or random. A coordinate relation indicates that the concept and relatum belong to the same semantic class. A hypernym relation indicates that the relatum is a category of which the concept is a specific instance. A meronym relation implies that relatum is a part/component/organ/member of the concept. An attribute relation is when the relatum is an adjective expressing an attribute of the concept. An event relation holds when the relatum is a verb referring to an action/activity/happening/event that is performed by or with the concept. If the relatum and concept are unrelated, the relation between them is 'random'. Classify your answers into coord, hyper, mero, attri, event, and random.
Input: Concept: missile, Relatum: short.
Output: | attri | 2 | NIv2 | task1418_bless_semantic_relation_classification | zs_opt | [
0.20295555889606476,
0.14809772372245789,
0.548879861831665,
-0.2695864140987396,
-0.25522932410240173,
-0.22379635274410248,
0.4291945695877075,
0.26463583111763,
0.4222392141819,
-0.8457459211349487,
-0.816757321357727,
0.1426636427640915,
-0.6784694790840149,
0.1394466608762741,
0.886... |
Detailed Instructions: This task is about translating a given Spanish language sentence to English.
See one example below:
Problem: Leeuwenhoek y Huygens... ...fueron abuelos de la medicina moderna:
Solution: Leeuwenhoek and Huygens... ...are the grandfathers of much of modern medicine.
Explanation: This is a good example because the Spanish sentence has been translated correctly to English.
Problem: Es 1.76 kilohertz.
Solution: | It's 1.76 kilohertz. | 4 | NIv2 | task1692_qed_amara_translation | fs_opt | [
-0.7025551795959473,
0.9956076145172119,
-0.15293286740779877,
-0.919712245464325,
-0.3450605869293213,
-1.166593313217163,
0.5732632875442505,
0.9220057725906372,
0.6348284482955933,
-0.7575230002403259,
-0.36880072951316833,
0.9210355877876282,
-0.16540199518203735,
0.5280309915542603,
... |
Teacher:You will be given a sentence that describes a restaurant. You will also be given a few categories of information regarding that sentence. Your task is to fill each of the categories with the appropriate information from the sentenece.
Teacher: Now, understand the problem? Solve this instance: Sentence: xname is a pub that provides family friendly meals at a cheap price and has 5 out of 5 customer ratings ; Categories: eattype, rating, familyFriendly
Student: | eattype[pub], rating[5 out of 5], familyFriendly[yes] | 6 | NIv2 | task1597_nyc_slot_filling | zs_opt | [
-0.6677119135856628,
0.6136078238487244,
-0.3829837143421173,
-0.4212116301059723,
-0.36043357849121094,
0.019428761675953865,
0.8694067597389221,
0.8320377469062805,
0.6752016544342041,
-0.3477976322174072,
0.47154974937438965,
-0.3707873821258545,
-0.8411512970924377,
-0.3863251805305481... |
instruction:
Given the Target and Argument texts detect the stance that the argument has towards the topic. There are three types of stances "in favor", "against", and "neutral".
question:
Topic: Crime cameras
Argument: Crime cameras often have no one watching due to limited resources.
answer:
against
question:
Topic: War on Drugs
Argument: Legalizing drugs would improve quality control.
answer:
against
question:
Topic: Polygamy
Argument: Polygamy undermines the traditional institution of marriage.
answer:
| against
| 9 | NIv2 | task209_stancedetection_classification | fs_opt | [
-0.3966466784477234,
-0.25434237718582153,
0.10678622126579285,
-0.5027855634689331,
0.08590482920408249,
-1.0765039920806885,
0.3133201599121094,
0.7480942606925964,
0.6567956209182739,
0.2271638810634613,
-0.42838558554649353,
0.22205844521522522,
-0.39152419567108154,
-0.616797804832458... |
You are given a sentence in Galician. Your job is to translate the Galician sentence into Japanese.
E o primeiro, e vou dicir unha herexía aquí, ningún deles fai exercicio, cando menos na forma en que nós concibimos o exercicio.
まず最初はこれには異論をつぶやきたいのですが誰も運動を、つまり我々が考えるような運動をしていません
Imprimín máis de 3000 postais coa miña dirección, xusto coma esta.
返信用葉書を３千枚印刷しましたちょうどこんな感じのです
Unhas semanas máis tarde, ledes no xornal oh, a propósito, un cuarto deles morreu.
| 何週間後かに記事を目にします「ところでその4分の1が死んでしまった」と
| 0 | NIv2 | task1239_ted_translation_gl_ja | fs_opt | [
-1.0790491104125977,
0.6884981393814087,
0.006765011698007584,
-0.682584285736084,
-0.0873052254319191,
-0.1287238895893097,
0.9449335336685181,
0.08522266894578934,
0.06426230072975159,
-1.2600176334381104,
-0.9597921371459961,
-0.36712151765823364,
-0.3286186456680298,
0.1742681562900543... |
Given the task definition, example input & output, solve the new input case.
You are given a sentence in Polish. Your job is to translate the Polish sentence into Farsi.
Example: EM: Owszem. Ważne jest by rakieta mogła wrócić do lądowiska i wystartować ponownie w ciągu kilku minut.
Output: ایلان: درسته. این مهمه که بخش های راکت بتونند برگردند و بتونند به سایت پرتاب برگردند و اماده پرتاب باشند در عرض چند ساعت.
The Polish sentence is correctly translated into Farsi, because the meaning is preserved.
New input case for you: Słyszeli coś o Diecie South Beach, lub o Diecie Atkinsa.
Output: | آنها ممکن است در مورد رژیم غذایی ساحل جنوبی یا رژیم غدایی اتکینز شنیده باشند | 1 | NIv2 | task1263_ted_translation_pl_fa | fs_opt | [
-0.49086880683898926,
0.6148170828819275,
0.48638904094696045,
-0.14445307850837708,
-0.7511980533599854,
0.7100560665130615,
1.2480740547180176,
0.4463120102882385,
-0.04794410243630409,
-0.6089189052581787,
-0.5098922252655029,
0.6977194547653198,
-0.7874658703804016,
0.25967949628829956... |
This task is about translating a given English language sentence to Spanish.
--------
Question: Well there are 3 things that we need to remember going forward to help our children, because they're in trouble.
Answer: Hay 3 cosas que necesitamos recordar para ayudar a nuestros niños, porque están en peligro.
Question: And putting a little bit of that on your guitar pick really helps you grip it quite a lot. Especially if you sweat a lot.
Answer: Y poner un poquito de eso en la púa, ayuda bastante a agarrarla.
Question: Maaaan!
Answer: | tio!
| 7 | NIv2 | task1691_qed_amara_translation | fs_opt | [
-0.3310941457748413,
0.6568124294281006,
-0.7628912925720215,
-0.44155919551849365,
-0.6138266921043396,
-1.1654033660888672,
1.3711490631103516,
1.0813099145889282,
0.0766778439283371,
-0.44082409143447876,
-0.3611208200454712,
1.0439563989639282,
-0.7324872016906738,
-0.2089844048023224,... |
You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Spanish.
結局彼女たちはそんな制約を当然だと受け入れて成長したのです | Después de todo, ellas han crecido aceptando tales restricciones como normas. | 0 | NIv2 | task1223_ted_translation_ja_es | zs_opt | [
-0.5259809494018555,
0.6724498867988586,
-0.23699143528938293,
-0.29000145196914673,
-0.6393083930015564,
-0.12128091603517532,
0.04642334207892418,
0.7312763929367065,
1.0019378662109375,
-0.7859678268432617,
-0.31988513469696045,
-0.02477899380028248,
-1.0459215641021729,
0.3756139874458... |
You will be given a definition of a task first, then some input of the task.
You are given a sentence in Persian. Your job is to translate the Farsi sentence into Galician.
به جای آن, زندگی خود را برپا می کنند آنها به صورت مداوم به سمت یک فعالیت فیزیکی می روند
Output: | En vez diso, organizan as súas vidas de xeito que sexa necesario realizar actividade física. | 1 | NIv2 | task1270_ted_translation_fa_gl | zs_opt | [
-0.5571503043174744,
1.0234332084655762,
-0.2667897343635559,
-0.19262349605560303,
-0.6046675443649292,
0.13100849092006683,
0.5811823606491089,
0.39132797718048096,
0.3159704804420471,
-0.09465096890926361,
-0.6359239816665649,
-0.014326616190373898,
-0.5936760306358337,
0.10568791627883... |
TASK DEFINITION: In this task, you are given a review of movie. Your task is to classify given movie review into two categories: 1) positive, and 2) negative based on its content.
PROBLEM: My kids recently started watching the reruns of this show - both the early episodes on the N, and the later ones on ABC Family - and they love it. (I wasn't aware the show had even lasted past the first or second season) I'm curious as to what prompted all of the cast changes - I've seen them described as "highly publicized," and yet a half hours searching efforts on the web have revealed nothing but endless comments on how the early episodes were so much better than the later episodes. (Personally, I don't see a whole lot of difference - the scripts and themes remain largely the same throughout - but they do lose some great people along the way) My daughter has put the DVDs on her wish list, so perhaps the land of special features and commentary will shed some light on all of this. I also wish they'd done some self-referential humor about the changes - like on "Boy Meets World" where they drop the little sister for an entire season or so, and when a different actor later shows up playing her, they ask her where she's been and she says "upstairs," or when early series token geek "Minkus" shows up for the high school graduation, they ask him where he's been and he says "over there," pointing to the part of the classroom never shown by the camera, before saying "Hey, Mr. Turner, wait up!" and running off screen (Mr. turner being another character who left) Oh well - maybe there will be an E true Hollywood story on this or something? I was just glad to see Aunt Hilda show up for the finale - she was always one of my favorites - it's too bad it couldn't have been a more encompassing cast reunion. (The Zelda candle just didn't cut it for me)
SOLUTION: positive
PROBLEM: Much underrated camp movie on the level of Cobra Woman, etc. Photographic stills resemble Rembrandt prints. Sometimes subtle dialog and hidden literate touches found throughout.
SOLUTION: positive
PROBLEM: I saw this at the premiere in MelbourneIt is shallow, two-dimensional, unaffecting and, hard to believe given the subject matter, boring. The actors are passable, but they didn't have much to work with given the very plodding and unimpressive script. For those who might have worried that Ned Kelly would be over-intellectualised, you can take comfort in the fact that this telling of the story is utterly without any literary depth at all, told entirely on the surface and full of central casting standards. However, it doesn't work as a popcorn film either. Its pacing is too off-kilter and its craft is too lacking to satisfy even on the level of a mundane actioner.I very much doubt Gregor Jordan could sit back and say to himself "this is the best I could have done with the material".Ned Kelly is a fascinating figure, and equally so is the national response to him. Possibly folk genius, possibly class warrior, possibly psychopath and probably all these things, he has dominated Australian true mythology for over 120 years. Once again, his story has failed miserably on the big screen.Such is life.
SOLUTION: | negative
| 8 | NIv2 | task284_imdb_classification | fs_opt | [
0.3803645372390747,
0.08624996244907379,
-0.5207772850990295,
-0.42412567138671875,
0.34776151180267334,
-0.2748013734817505,
1.5762965679168701,
1.0338127613067627,
0.06085433438420296,
-0.016861967742443085,
0.3779597878456116,
0.11498770117759705,
-0.604474663734436,
-0.0863732025027275... |
Teacher:In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.
Teacher: Now, understand the problem? Solve this instance: ['e', 'p', 'g', '7775', '1505', 'a', '4823']
Student: | e, p, g, a | 6 | NIv2 | task488_extract_all_alphabetical_elements_from_list_in_order | zs_opt | [
-0.27602511644363403,
-0.11438873410224915,
0.3026566505432129,
-0.4185781478881836,
0.118299201130867,
-0.6772797107696533,
0.8369106650352478,
0.25332871079444885,
-0.33258315920829773,
0.40761473774909973,
-0.24599671363830566,
-0.42853373289108276,
-0.11788462102413177,
-0.690483093261... |
TASK DEFINITION: Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.
PROBLEM: Evelyn entered the cellar. Aiden entered the cellar. The broccoli is in the green_treasure_chest. Aiden exited the cellar. Evelyn moved the broccoli to the red_cupboard. Phone rang. Aiden entered the master_bedroom. Evelyn entered the master_bedroom. Phone rang. The persimmon is in the green_cupboard. Phone rang. Evelyn exited the master_bedroom. Aiden moved the persimmon to the blue_bathtub. Aiden entered the front_yard. Alexander entered the front_yard. The eggplant is in the red_suitcase. Alexander exited the front_yard. Aiden moved the eggplant to the red_crate. Evelyn entered the hall. Abigail entered the hall. The banana is in the blue_cupboard. Abigail exited the hall. Evelyn moved the banana to the green_bottle. Where does Evelyn think that Abigail searches for the banana?
SOLUTION: blue_cupboard
PROBLEM: Phone rang. Ella entered the master_bedroom. Jacob entered the master_bedroom. The carrot is in the blue_treasure_chest. Jacob exited the master_bedroom. Ella moved the carrot to the blue_crate. Sophia entered the master_bedroom. Elizabeth entered the master_bedroom. The carrot is in the blue_crate. Elizabeth exited the master_bedroom. Sophia moved the carrot to the blue_treasure_chest. Sophia entered the den. Jacob entered the den. The spinach is in the red_bucket. Jacob exited the den. Sophia moved the spinach to the green_basket. Jacob entered the master_bedroom. Sophia entered the master_bedroom. The carrot is in the blue_treasure_chest. Sophia exited the master_bedroom. Jacob moved the carrot to the blue_crate. Where was the carrot at the beginning?
SOLUTION: blue_treasure_chest
PROBLEM: Phone rang. Emily entered the attic. Sophia entered the attic. The lime is in the green_pantry. Sophia exited the attic. Emily moved the lime to the blue_container. Emily entered the master_bedroom. Ella entered the master_bedroom. The pineapple is in the blue_suitcase. Ella exited the master_bedroom. Emily moved the pineapple to the blue_treasure_chest. Jackson entered the attic. Phone rang. Sophia entered the attic. The lime is in the blue_container. Sophia exited the attic. Jackson moved the lime to the green_pantry. Jackson entered the TV_room. Sophia entered the TV_room. The green_pepper is in the green_box. Sophia exited the TV_room. Jackson moved the green_pepper to the red_bucket. Where will Sophia look for the green_pepper?
SOLUTION: | green_box
| 8 | NIv2 | task154_tomqa_find_location_hard_noise | fs_opt | [
0.542359471321106,
-0.4904056787490845,
-0.3516649007797241,
-0.41124504804611206,
-0.007839921861886978,
0.028910387307405472,
0.24954621493816376,
0.6658850908279419,
0.026054907590150833,
0.0944390594959259,
0.1385437250137329,
0.572233259677887,
-0.4302120804786682,
-0.0336416810750961... |
Indicate if the following Polish tweet contains cyber-bullying content with 'Yes'; otherwise, respond with 'No'.
One example is below.
Q: Tweet: @anonymized_account @anonymized_account @anonymized_account Gdzie jest @anonymized_account . Brudziński jesteś kłamcą i marnym kutasem @anonymized_account, Question: Does the tweet contain cyberbullying (harmful) content?
A: Yes
Rationale: The tweet contains Bullying content
Q: Tweet: @anonymized_account Ciebie myszko osądzą wyborcy już niedługo. , Question: Is the tweet free of any cyberbullying (harmful) content?
A: | Yes | 9 | NIv2 | task839_cdt_classification | fs_opt | [
-1.318516492843628,
1.0977783203125,
0.6789906024932861,
0.5487780570983887,
-0.5534749031066895,
-1.037618637084961,
0.778125524520874,
-0.7625154256820679,
-0.08055438101291656,
0.16327449679374695,
-0.3853699564933777,
0.4511810541152954,
-0.5839989185333252,
-0.2743529677391052,
-0.4... |
Given the task definition and input, reply with output. In this task you are given an anecdote. You must find out whether the anecdote is something the author has done or is considering doing. Label the instances as "HISTORICAL" when the author has already done something and label them as "HYPOTHETICAL" when the author is considering doing something in the future.
She was constantly lying to me, whether it be out of kindness or to protect the relationship from heading towards an argument (meaning bad things she's done but has lied to keep me from questioning her). We've constantly had arguments with each other and she even started feeling like we weren't meant to be. So the 3rd time I broke it off, I felt sure I wasn't going to be with her, as I had no emotions. This was due to the fact that she is extremely selfish and wouldn't even console me when I was in a bad state. She then started to say things like I'll kill myself if you leave me, or she couldn't get attracted to other men. Being the asshole that I am, I decide to stick with her to make sure she stays safe, but I've really had enough at that point. Fast forward a few weeks later and the lies ensue. I face my fear of having a death on my soul and just tell her I've had enough with the lies, I break it off for the last time and she's quiet for a few days. She hasn't killed herself at that point as I've seen her online and she's tried to message me, (I've blocked her everywhere). Then I get messages from her on Instagram somehow, saying she'll actually kill herself, and I replied with "well atleast you won't be able to hurt anyone".......
I'm not familiar with Instagram but I think if their profile picture disappears they've blocked you? Correct me if I'm wrong. But I'm feeling guilty as fuck and anxiety is eating me alive. I'm religious, so having a death on me is.. Idk how to feel. AITA?
| HISTORICAL | 5 | NIv2 | task282_scruples_event_time | zs_opt | [
0.20570147037506104,
0.33120280504226685,
0.193048357963562,
-0.030390482395887375,
-0.17046938836574554,
-0.7728404998779297,
0.38887375593185425,
0.7189503312110901,
-0.2966340184211731,
-0.0978921502828598,
-0.6983659267425537,
0.038845621049404144,
-0.5901350378990173,
-0.0431597791612... |
In this task, you are given a sentence and a profession. The sentence mentions two professions: one's gender is identifiable using the gendered pronouns in the text and the other's gender is unidentifiable. You are expected to return whether the given profession's gender is identifiable or unidentifiable.
Sentence: The driver smiled at the attendant and asked him when to pick the boss.
Profession: driver | Unidentifiable | 0 | NIv2 | task351_winomt_classification_gender_identifiability_anti | zs_opt | [
-1.3794341087341309,
0.5428293943405151,
0.2840428352355957,
-0.6084741353988647,
-0.10716957598924637,
0.24011889100074768,
-0.16968519985675812,
1.1215349435806274,
0.7472885847091675,
0.23835259675979614,
-1.1027218103408813,
-0.3687378168106079,
0.2884267568588257,
-0.41323626041412354... |
In this task you will be given a list, of lists, of numbers. Each list is presented with brackets and comma-separated values. For example, a list of numbers is [1,2,3] and a list of two lists of numbers is [[1,2],[3,4,6]]. You should sum up the values at every position of every inner list and put it as an element of your answer, that is, you should sum the first members of each inner list together and put it as the first element of the list, then sum the second members of each inner list together and put it as the second element of your list, etc. The output should be a list of numbers with the same length as the longest inner list.
Q: [[-32, 85, -66, 24, 19, -52], [73, 40, 37, 82, -26, -96, 42, -3], [-38, 100, 70, 95, -22, -97, -23, 90], [-69, 73, 32, -59, -80, 40, -41, -11, 28], [-26, -4, -45, 58, -2, 87, 39], [-20, 52, -71, -30, 23, -54, 80, -13, -55], [-4, 12, 92, 29, -91]]
A: | [-116, 358, 49, 199, -179, -172, 97, 63, -27] | 4 | NIv2 | task122_conala_list_index_addition | zs_opt | [
-0.145683154463768,
-0.43440067768096924,
-0.43136757612228394,
-0.47886502742767334,
0.23808300495147705,
-0.2964320778846741,
0.7852182388305664,
0.5168708562850952,
-0.49018633365631104,
-0.005883019417524338,
-0.4225005507469177,
0.2538406252861023,
-0.4925619959831238,
0.0697236880660... |
Given the task definition, example input & output, solve the new input case.
In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story incoherent / implausible by indicating 1 or 2 in the output. If both sentences are plausible, pick the one that makes less sense.
Example: Beginning: Butch had a really old computer. Middle 1: Butch decided to order a new computer online. Middle 2: Butch noticed that a storm was approaching to his town. Ending: It arrived and Butch was much happier.
Output: 2
People generally don't feel happy about natural disasters like storms. Therefore, we choose 2 in this case.
New input case for you: Beginning: A man organized a lottery pool at his work. Middle 1: The lottery tickets were all winners. Middle 2: The lottery tickets did not win. Ending: He told them next time they would win.
Output: | 1 | 1 | NIv2 | task070_abductivenli_incorrect_classification | fs_opt | [
-0.3245023488998413,
0.39965569972991943,
-0.02515910007059574,
0.31968605518341064,
0.07790378481149673,
0.04180290922522545,
0.08604580163955688,
1.0582531690597534,
0.0047316886484622955,
0.19189807772636414,
-0.547633707523346,
0.0702969878911972,
0.2090299427509308,
-0.417570710182189... |
In this task you will be given two dialogues. You need to determine if both dialogues have the same underlying emotion. The possible emotions are happy, sad, angry, or other. If they do output 'yes', if not output 'no'.
[Q]: Dialogue 1: 'preparation all the best hirika d who is hirika'. Dialogue 2: 'facewithtearsofjoyfacewithtearsofjoyfacewithtearsofjoyfacewithtearsofjoywoah that was so boring facewithtearsofjoyfacewithtearsofjoyfacewithtearsofjoyfacewithtearsofjoyfacewithtearsofjoy see i'm so funny oh u think u r funny'.
[A]: no
[Q]: Dialogue 1: 'i don't know what what's your nick name'. Dialogue 2: 'but how get your strength up i lost all my hopes'.
[A]: no
[Q]: Dialogue 1: 'haa so u r only time passing like me p it's so funny'. Dialogue 2: 'yeah normally good with me but not with my gf sounds like a keeper you are idiot'.
[A]: | no
| 5 | NIv2 | task518_emo_different_dialogue_emotions | fs_opt | [
-0.43173617124557495,
0.2816509008407593,
0.6825878620147705,
-0.42469412088394165,
-0.28071171045303345,
-0.2664039731025696,
1.3030128479003906,
0.21836629509925842,
0.36491236090660095,
-0.49379730224609375,
-0.3996371328830719,
-0.7515596151351929,
-0.33805596828460693,
0.1006008088588... |
TASK DEFINITION: In this task, you are given two strings A,B. You must perform the following operations to generate the required output list: (i) Find the longest common substring in the strings A and B, (ii) Convert this substring to all lowercase and sort it alphabetically, (iii) Replace the substring at its respective positions in the two lists with the updated substring.
PROBLEM: bWEOTqnZlWWGL, RXcvdqnZlWWywbjDo
SOLUTION: bWEOTlnqwwzGL, RXcvdlnqwwzywbjDo
PROBLEM: SOuKXOeNMcEtkePLnZdhaAEkjQdWQEinrsRV, fizRyPLnZdhaAEkjQdWQSBkzprenEkF
SOLUTION: SOuKXOeNMcEtkeaaddehjklnpqqwzEinrsRV, fizRyaaddehjklnpqqwzSBkzprenEkF
PROBLEM: YihgpTqIOX, BjPgpTqhDlG
SOLUTION: | YihgpqtIOX, BjPgpqthDlG
| 8 | NIv2 | task755_find_longest_substring_and_replace_its_sorted_lowercase_version_in_both_lists | fs_opt | [
0.6778610944747925,
0.3431251049041748,
-0.2581155002117157,
-0.2381371259689331,
0.41345009207725525,
0.23609496653079987,
0.3055688142776489,
0.22067226469516754,
-0.4362705647945404,
-0.3049874007701874,
-0.8709248304367065,
-0.6964460015296936,
-0.2888100743293762,
-0.13247862458229065... |
Definition: Given a sentence in Arabic, generate a new Arabic sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.
Input: « يمكن للمعلِّم أن يري » يري « منضدة » منضدة « كيف يُحل النص » أي اللوح المحفوظ في اللوح المحفوظ.
Output: | يمكن للمعلّم أن يُظهر للقسم كيف يُحَلّ الإحتيال. | 2 | NIv2 | task414_mickey_ar_sentence_perturbation_generation | zs_opt | [
0.24321042001247406,
0.07084646075963974,
0.5177685618400574,
-0.2627522051334381,
-0.5077557563781738,
-0.019645340740680695,
0.33147573471069336,
0.2644018828868866,
0.7574829459190369,
-0.5121171474456787,
-1.2129449844360352,
-0.3098217248916626,
-1.1120755672454834,
0.5494988560676575... |
In this task, you're given four sentences of a story written in natural language. The given story is not complete and your job is to complete the story by selecting one of the sentence choices from (A) and (B), such that the story sounds fully coherent.
One example: Sentence1: Rick grew up in a troubled household. Sentence2: He never found good support in family, and turned to gangs. Sentence3: It wasn't long before Rick got shot in a robbery. Sentence4: The incident caused him to turn a new leaf.
(A) He is happy now. (B) He joined a gang.
Solution is here: A
Explanation: As mentioned in fourth sentence, the incident turned a new leaf to Rick's life; so, he must be happy now.
Now, solve this: Sentence1: Sam moved to Los Angeles to become a movie star. Sentence2: He did not have much money but he thought that going is the only way. Sentence3: After two months sam was sleeping in his car and broke. Sentence4: He went to the chinese theater to beg one day.
(A) Sam felt quite hopeful. (B) Sam felt very depressed.
Solution: | B | 6 | NIv2 | task296_storycloze_correct_end_classification | fs_opt | [
-0.3362070620059967,
0.7612736225128174,
-0.3876263201236725,
-0.2744988203048706,
0.03847123682498932,
-0.3416723906993866,
0.4601985216140747,
0.9442518949508667,
0.1343763768672943,
0.30949831008911133,
-0.15003818273544312,
0.1264532059431076,
-0.4542474150657654,
-0.21638280153274536,... |
You are given a sentence in English. Your job is to translate the English sentence into Spanish.
Let me give you an example: With economic growth, countries and societies enter into a virtuous cycle of upward mobility, opportunity and improved living standards.
The answer to this example can be: Con el crecimiento, los países y las sociedades ingresan en un ciclo virtuoso de movilidad ascendente, de oportunidad y mejores niveles de vida.
Here is why: The English sentence is correctly translated into Spanish, because the meaning is preserved.
OK. solve this:
So I've studied a lot about stem cells — embryonic stem cells are particularly powerful.
Answer: | He estudiado mucho sobre células madre; las células madre embrionarias son especialmente potentes. | 8 | NIv2 | task1219_ted_translation_en_es | fs_opt | [
-0.7747423648834229,
0.2358660101890564,
0.27306872606277466,
-0.2447461485862732,
-0.24851281940937042,
-0.7212854027748108,
-0.057081952691078186,
1.045464277267456,
-0.21011069416999817,
-0.34418147802352905,
-0.664608359336853,
0.4561486840248108,
-0.7023116946220398,
-0.05068223178386... |
Definition: In this task, you're given a review from Amazon. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good.
Input: The hooks were separated from the body of three of the hangers during shipping and I was unable to reattach them. They went right into the garbage. I would not recommend this product at all.
Output: | 1 | 2 | NIv2 | task1310_amazonreview_rating_classification | zs_opt | [
-0.056190375238657,
-0.30077382922172546,
-0.06267165392637253,
0.21367427706718445,
0.40894097089767456,
-0.06894458830356598,
0.8119462728500366,
0.5331226587295532,
-0.4516337513923645,
0.6784496307373047,
-0.817101776599884,
0.051665641367435455,
-0.4081882834434509,
0.1304765045642852... |
Detailed Instructions: In this task, you are given two sentences in the English language and your task is to classify them into one of their discourse types. A discourse type is an indicator to classify the given two sentences on the basis of a co-text as well as a relevant context. There are 13 discourse types in total which are 'SINGLE_S_COORD', 'SINGLE_CATAPHORA', 'SINGLE_CONN_INNER', 'SINGLE_APPOSITION', 'SINGLE_VP_COORD', 'SINGLE_CONN_START', 'PAIR_ANAPHORA', 'PAIR_CONN', 'SINGLE_RELATIVE', 'SINGLE_CONN_INNER_ANAPHORA', 'SINGLE_S_COORD_ANAPHORA', 'PAIR_CONN_ANAPHORA' and 'PAIR_NONE'.
Problem:Sentence 1:It is always at amateur level . Sentence 2:However , lacrosse in Scotland goes back to 1890 at St Leonards School , Fife , where women 's lacrosse had been introduced by Louisa Lumsden .
Solution: | PAIR_CONN | 8 | NIv2 | task564_discofuse_classification | zs_opt | [
0.1461438089609146,
0.07906819880008698,
-0.22136889398097992,
-0.7952036261558533,
0.7567755579948425,
-0.25636783242225647,
-0.12669530510902405,
0.5650152564048767,
-0.057900041341781616,
-0.14119145274162292,
-0.1788066327571869,
0.43024754524230957,
-0.032529547810554504,
0.0134628517... |
The input is a tweet which can be classified as Hate Speech, Offensive or Normal. Given such a tweet, output the class the tweet belongs to. Hate Speech will contain threatening language towards the community targeted. Offensive language will contain abusive or discriminatory language towards the community targeted.
One example is below.
Q: cowardly actions by the pussy brits men let their women be gangraped by moslim animals should change countrys name to cuckland
A: Hate Speech
Rationale: This tweet targets Muslim community in a violent context. Hence this is Hate Speech.
Q: atp i need to fuck w a <number> old man that ’ the only way a nigga gone ever understand what i ’ m saying
A: | Hate Speech | 9 | NIv2 | task1502_hatexplain_classification | fs_opt | [
-0.4706948399543762,
0.7170355319976807,
0.5010339617729187,
0.3729887008666992,
-0.28102585673332214,
-1.102887749671936,
-0.015497819520533085,
0.3634493947029114,
0.3375932574272156,
0.3236508369445801,
-0.4931124746799469,
-0.011136932298541069,
-0.7650773525238037,
-0.978685736656189,... |
You are given a sentence in Polish. Your job is to translate the Polish sentence into English.
One example: To największa nagrywarka, jaką w życiu widzieliście.
Solution is here: It's sort of the biggest TiVo box you've ever seen.
Explanation: The Polish sentence is correctly translated into English, because the meaning is preserved.
Now, solve this: Wiemy, że nasze społeczeństwa muszą się radykalnie zmienić.
Solution: | We know our societies have to radically change. | 6 | NIv2 | task1256_ted_translation_pl_en | fs_opt | [
-0.23663003742694855,
0.9495629072189331,
0.9883164763450623,
0.15854880213737488,
0.21333113312721252,
-0.6450714468955994,
0.41877591609954834,
-0.1803554743528366,
0.14668498933315277,
0.04166988283395767,
0.4756354093551636,
0.362861692905426,
-1.1266398429870605,
-0.04054158926010132,... |
Definition: Given a sentence in the Japanese and Lao language. Your task is check if the Lao sentence is translation of Japanese. if the translation is correct than generate label "Yes", otherwise generate label "No".
Input: Japanese: 国連人権高等弁務官のナビ・Pillayによると、5,000人以上がシリア蜂起で殺害され、約300人の子供が含まれている計算になる。
Lao: ອີງຕາມທ່ານ ນາວິ ບິເລ ກໍາມະທິການຂັ້ນສູງ ເພື່ອສິດທິມະນຸດ ສະຫະປະຊາຊາດ ປະຊາຊົນຫລາຍກວ່າ 5,000 ຄົນ ໄດ້ຖືກຂ້າເສຍຊີວິດ ໃນລະຫວ່າງການລຸກຮື້ຂຶ້ນ ໃນປະເທດຊີເຣຍ ຕົວເລກແມ່ນລວມເອົາເດັກນ້ອຍ ປະມານ 300 ຄົນ.
Output: | Yes | 2 | NIv2 | task1126_alt_ja_lo_answer_generation | zs_opt | [
-0.7204718589782715,
-0.5466132164001465,
-0.22074007987976074,
0.3921898603439331,
0.006876417901366949,
-0.09848202764987946,
0.9571778178215027,
0.7484439015388489,
-0.33852601051330566,
0.13127489387989044,
-0.6014469861984253,
0.494120717048645,
-0.9212316870689392,
0.6690824031829834... |
TASK DEFINITION: Indicate if the following Polish tweet contains cyber-bullying content with 'Yes'; otherwise, respond with 'No'.
PROBLEM: Tweet: @anonymized_account Wszystko plus otyłość, bajpasy i proteza biodra , Question: Does the tweet contain cyberbullying (harmful) content?
SOLUTION: No
PROBLEM: Tweet: from: me\nto: wszystkie ładne dziewczyny\n\njak to jest być ładnym???? , Question: Does the tweet contain cyberbullying (harmful) content?
SOLUTION: No
PROBLEM: Tweet: @anonymized_account @anonymized_account To jest bardzo dobre pytanie 😂 , Question: Does the tweet contain cyberbullying (harmful) content?
SOLUTION: | No
| 8 | NIv2 | task839_cdt_classification | fs_opt | [
-0.816097617149353,
1.091109037399292,
0.13660529255867004,
0.3727577328681946,
-0.743955135345459,
-0.3756597340106964,
0.7075613737106323,
-0.4930432438850403,
0.3517564833164215,
0.11417387425899506,
-0.6316657066345215,
0.07313355803489685,
-1.075905680656433,
0.01079266332089901,
0.... |
Given a simple high-school level math question, you are required to solve it and provide the final answer. The final answer is always a single number. These questions can range from a variety of topics like simple arithmetic, solving equations, converting a quantity from one unit to another, finding remainders/GCD/LCM, finding probabilities etc. Each question has only one correct answer. This answer can be a positive or negative integer, a fraction or a decimal number. If the answer is a negative number use the hyphen (e.g. -42) symbol for the minus sign. For decimal numbers, do not add extra zeros after the decimal point. For fractional numbers, separate the numerator and denominator using a forward slash (e.g. 3/25).
--------
Question: What is prob of picking 1 q and 1 z when two letters picked without replacement from qqzqqqqzq?
Answer: 7/18
Question: Suppose -5*j + 6*j - 5 = 0. Solve j*y - 5 = -3*u, 5*y - u = -1 - 14 for y.
Answer: -2
Question: What is 330.9 - 0.7?
Answer: | 330.2
| 7 | NIv2 | task835_mathdataset_answer_generation | fs_opt | [
-0.6015241146087646,
0.48487627506256104,
-0.049538109451532364,
-0.6542550325393677,
0.5024376511573792,
-0.09333831816911697,
1.0745799541473389,
0.3785286545753479,
-0.0852176770567894,
-0.6923877000808716,
-0.5827462673187256,
0.11547097563743591,
-0.37259596586227417,
0.46735450625419... |
Given the task definition and input, reply with output. Given a set of five words, generate the word from the set that does not belong (i.e. is the least relevant) with the other words. Words are separated by commas.
crane, hoist, egret, tackle, ostrich
| hoist | 5 | NIv2 | task142_odd-man-out_classification_no_category | zs_opt | [
-0.00442835409194231,
0.8072553873062134,
0.32948338985443115,
0.000989554449915886,
0.0727880671620369,
-0.2768074572086334,
0.38222092390060425,
-0.15439996123313904,
0.21340259909629822,
-0.628829836845398,
-0.9668932557106018,
-0.40355920791625977,
-0.6319484710693359,
0.38316631317138... |
You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Farsi.
One example is below.
Q: אתם רואים שהפינגווין הזה ניגש ומסתכל על החוטים, הוא לא אוהב את החוט הזה.
A: شما میتونید این پنگوئن ها رو ببینید اونها حرکت میکنند به اون سیمها نگاه میکنند ولی شبیه اون سیمها نیستند
Rationale: The Hebrew sentence is correctly translated into Farsi, because the meaning is preserved.
Q: מאידך, מצאנו שמילות סיסמה שניתנות לביטוי עבדו מעולה, באופן מפתיע. אז אנחנו כרגע חוקרים לעומק על מנת לראות אם נוכל לפתח את הגישה הזו.
A: | از طرفی دیگه متوجه شدیم که کلمه عبور تلفظی به خوبی جواب گوست ، پس ما تحقیقات بیشتری رو در این مورد انجام دادیم و ببینیم می تونیم از این نوع کلمات عبور استفاده ی بهتری ببریم. | 9 | NIv2 | task1113_ted_translation_he_fa | fs_opt | [
-1.2186267375946045,
0.7406445741653442,
0.013901682570576668,
0.2747591435909271,
-0.449656218290329,
-0.7271038889884949,
0.45742636919021606,
0.12396054714918137,
0.49748149514198303,
0.07919265329837799,
-0.9654251337051392,
0.5653074979782104,
-0.9492901563644409,
-0.04359778016805649... |
Given the task definition and input, reply with output. In this task, you need to count the number of words in a sentence that contain the given letter
Sentence: 'a stop sign casting a shadow of a sign that says war'. How many words contain the letter 'y' in the sentence.
| 1 | 5 | NIv2 | task161_count_words_containing_letter | zs_opt | [
-0.5028010606765747,
0.8021467924118042,
0.30307456851005554,
-0.4064159095287323,
-0.09424516558647156,
0.012187538668513298,
-0.4279634654521942,
0.8787990808486938,
0.9224562048912048,
-0.3861571252346039,
-0.08752542734146118,
0.05667546018958092,
-0.012268489226698875,
-0.098591580986... |
instruction:
You are given a passage. You need to construct a question about the information present in the passage. Construct a question in such a way that (i) it is unambiguous, (ii) its answer is the whole paragraph. Avoid creating questions that can be answered correctly without actually understanding the paragraph.
question:
Leonard Grey III
answer:
who is the first president in Jamaica?
question:
How about the lack of personal responsibility for one's own actions these days?
answer:
What is the best social problem to talk about in a 10th grade student essay?
question:
Coffee trade...\nhttp://www.brewbar.com/ethiopia.htm\nWeblog...\nhttp://madeinethiopia.net/saveethiopia/\nNews...\nhttp://www.journalismnet.com/africa/ethiopia.htm
answer:
| about ethiopian import trade?
| 9 | NIv2 | task1594_yahoo_answers_topics_question_generation | fs_opt | [
0.021647106856107712,
0.46278637647628784,
-0.07847653329372406,
-0.580895185470581,
-0.012639511376619339,
-0.4692184627056122,
0.4855332374572754,
0.504957377910614,
-0.2920057773590088,
0.25135713815689087,
-0.32467204332351685,
0.06027776747941971,
-1.0489609241485596,
-0.2993105947971... |
Teacher:In this task, you're given an article and an answer. Your task is to generate the question for the answer based on the given article.
Teacher: Now, understand the problem? Solve this instance: Article: Are you planning to visit Britain? Here are a few suggestions for a beautiful weekend away. Bournemouth This famous tourist town has 11 km of beautiful beaches. Last year, 10,000 tourists visited this beautiful town. It's the perfect place to go swimming or sailing. There are lots of lovely parks and gardens to visit and it's a great place to eat out. You can also go to a classical concert or go dancing in one of the nightclubs. Stratford-upon-Avon This was William Shakespeare's hometown. He spent most of his life in this town and wrote his plays here. You can visit his house or see his plays at one of the Royal Shakespeare Company's theatres. There are some interesting museums and lots of beautiful 500-year-old house. You can also go on boat trips and visit traditional English villages. Alford Deep in the Lincolnshire countryside is the pleasant market town of Alford. It is known for its five-sailed windmill . Have a walk round this lovely old place and you'll see many pleasant houses from as far back as the 17thcentury. Captain James Smith, who was one of the founders of James town in Virginia, USA, was educated in Alford. Bath Most people come here to see the 2,000-year-old Roman Baths. But this city is also famous for its beautiful 18thcentury buildings and was the home of the writer Jane Austen. You can learn about her life at the Jane Austen Centre near Queen's Square. In the past, Bath was also popular with the royal family and Queen Elizabeth I spent one or two weeks every year here.
Answer: Visit fishing villages.
Student: | What can visitors do in Bournemouth? | 6 | NIv2 | task311_race_question_generation | zs_opt | [
0.4926725924015045,
0.8696922063827515,
-0.25369584560394287,
-0.7417669296264648,
0.6792821884155273,
-1.167559027671814,
0.2440914511680603,
0.5080971717834473,
-0.2593706250190735,
-0.006638647988438606,
0.17668651044368744,
1.2266123294830322,
-1.1213710308074951,
-0.3490438461303711,
... |
Q: Given a factoid/trivia type question, generate the topic of the question. The topic is the entity the question talks about.
Which painter, along with Georges Braque, founded the style cubism in the early 20th century?
A: | cubism | 7 | NIv2 | task899_freebase_qa_topic_generation | zs_opt | [
-0.18314164876937866,
1.215955376625061,
0.1999264508485794,
-0.27697253227233887,
-0.5776405930519104,
-0.1391676813364029,
0.7567392587661743,
-0.9550994634628296,
0.23247548937797546,
-0.28795021772384644,
-0.2719533443450928,
0.7433335781097412,
-0.4559740424156189,
0.2684231996536255,... |
Given a category and a set of five words, find the word from the set that does not belong (i.e. is the least relevant) with the other words in the category. Words are separated by commas.
Q: Category: temperature
Words: hot, refreshing, popular, tropical, cool
A: | popular | 4 | NIv2 | task141_odd-man-out_classification_category | zs_opt | [
0.8882864713668823,
-0.022351795807480812,
-0.3624786138534546,
0.478768914937973,
0.2711818218231201,
-1.6888203620910645,
0.3838501572608948,
-0.3998940885066986,
-0.3736326992511749,
-0.360270619392395,
-0.2965824007987976,
-0.16326671838760376,
-0.6203488111495972,
-0.08034153282642365... |
You are given a question or fill-in-the-blank question, two answer options (Option1 and Option2) and an Explanation. Your task is to find the correct answer (return the string of the correct option, not option1/2) for the given question from the given options and using explanation.
Example input: Question: The government of Canada is considering implementing less carbon taxes across the country. If these taxes were implemented, the amount of carbon dioxide emissions in the country would be expected to
Option1: fall
Option2: rise
Explanation: The carbon taxes encourage people to use less fossil fuel, which reduces carbon dioxide emissions.
Example output: rise
Example explanation: As mentioned in the Qualitative Statement, due to taxes people will reduce usage of fossil fuel and hence, carbon dioxide emission will also reduce. So, if Camada government decrease the tax, people will use it more and hencce, emission will also incerase.
Q: Question: The ball began to raise slowly above the table. The higher it rises above the table, the potential energy will
Option1: decrease
Option2: increase.
Explanation: So the higher an object is above a surface, the more potential energy it has.
A: | increase. | 3 | NIv2 | task178_quartz_question_answering | fs_opt | [
-0.4096008837223053,
0.35850048065185547,
-0.3253662586212158,
-0.20376867055892944,
0.011760937049984932,
-0.48024803400039673,
0.2811049520969391,
1.2191606760025024,
-0.3118175268173218,
0.26016250252723694,
-0.42883288860321045,
-0.2256699502468109,
-0.6696250438690186,
0.1099754869937... |
Given the task definition and input, reply with output. In this task you are given a small conversation between two persons and 4 options on how the conversation should continue. Your job is to choose the most reasonable option. The conversation and the options are separated by a newline character. Each dialogue in the conversation are separated by a comma. F and M indicate female and male, respectively.
M: Mary, what's that there in your hand? A ring? ,F: Yes, you are right. It's a birthday gift for my grandma. ,M: But you only gave me a jacket for my birthday last week.
(A) F: This is a ring for my grandma. (B) F: I am sorry. You spoke so rapidly that I did not catch the meaning of what you said. Could you repeat that? (C) F: I gave you a ring for your birthday last week. (D) F: I will send this jacket as a birthday gift for my grandma.
| A | 5 | NIv2 | task611_mutual_multi_turn_dialogue | zs_opt | [
-0.06906149536371231,
0.8171321153640747,
-0.1363518238067627,
-0.253460168838501,
0.06152128800749779,
-0.10665401071310043,
0.3742545545101166,
0.6946855187416077,
0.3333593010902405,
0.00757147092372179,
-0.6091461181640625,
-0.10596587508916855,
0.31599345803260803,
-0.4114692211151123... |
In this task, you need to translate the given English sentence to Polish language.
One example: The Americans didnt even know
Solution is here: Amerykanie nawet nie wiedzieli
Explanation: English sentence is properly converted into Polish sentence
Now, solve this: That's Mercury. This is Venus.
Solution: | To Merkury, to jest Wenus. | 6 | NIv2 | task830_poleval2019_mt_translation | fs_opt | [
-0.0005532531067728996,
1.4513622522354126,
0.06215173378586769,
-0.05363929271697998,
-0.48392680287361145,
-1.113187313079834,
0.6387855410575867,
-0.136431023478508,
1.240349531173706,
-0.6121811270713806,
-0.2522028684616089,
0.12053601443767548,
0.17649328708648682,
-0.491272807121276... |
Instructions: In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonX will be affected as mentioned in the Tail or not. These effects are social actions that may occur after the Head event. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Input: Head: PersonX lasts two hours<sep>Tail: become exhausted
Output: | Yes | 3 | NIv2 | task1200_atomic_classification_xeffect | zs_opt | [
0.4387228190898895,
0.21436002850532532,
0.10535889118909836,
-0.3665751814842224,
-0.7811586260795593,
-1.0149292945861816,
1.4276390075683594,
0.21426953375339508,
-0.36405205726623535,
-0.6244809627532959,
-0.39566707611083984,
-0.39448195695877075,
-0.525597333908081,
0.128809943795204... |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
Given a phrase describing the relationship between two words, extract the words and the lexical relationship between them. The relation has to be of the type 'MemberOf', 'MadeOf', 'Synonym', 'Entails', 'HasA', 'HasProperty', 'PartOf', 'Antonym' or 'IsA'. The output should have the format: word1 relation word2.
account can be used with the same meaning of report
Solution: account Synonym report
Why? The output is correct as the input describes the relationship between account and report, and the relation is that of having the same meaning, therefore they have a Synonym relationship.
New input: practice can be used as the opposite of theory
Solution: | practice Antonym theory | 0 | NIv2 | task1510_evalution_relation_extraction | fs_opt | [
0.1876535713672638,
0.8714605569839478,
-0.17640219628810883,
-0.09377598762512207,
-0.06745383888483047,
-0.4749273955821991,
0.2879248261451721,
0.7062842845916748,
0.6699146032333374,
-0.41121387481689453,
-0.39113539457321167,
0.10840378701686859,
-0.4184819161891937,
-0.08547586202621... |
A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence.
Let me give you an example: اس کے تحت اس عمل کو قابل سزاعمل بنانے کی بھی تجویز ہے ،جس کے تحت تین برسوں تک کی قیداور جرمانہ عائد کیاجائیگا ۔
The answer to this example can be: ഇതിന് കീഴിൽ, സാധുവായ ശിക്ഷ നൽകാനും നിർദ്ദേശിക്കപ്പെടുന്നു, അതിൽ മൂന്ന് വർഷം തടവുകാരനായിരിക്കും.
Here is why: Correct translation for given sentence. Input sentence means 'Under this, it is also suggested to make a valid punishment, under which three years will be prisoner.' which is the same as the output sentence.
OK. solve this:
بانڈ منڈی کو مضبوط بنانے کے اقدامات
Answer: | ബോണ്ട് വിപണി വിപുലീകരിക്കാന് നടപടികള് | 8 | NIv2 | task1060_pib_translation_urdu_malayalam | fs_opt | [
-0.17724356055259705,
1.1676442623138428,
-0.5304105281829834,
-0.43310970067977905,
0.05029661953449249,
-0.6335723400115967,
0.13444682955741882,
0.37197524309158325,
0.06878345459699631,
0.09100830554962158,
-0.8865562677383423,
0.19927701354026794,
-0.6109411716461182,
0.14535425603389... |
In this task, you're given reviews from Amazon's food products and a summary of that review. Your task is to classify whether the given summary matches the original review. Generate "True" if the given review and its summary match, otherwise generate "False".
Let me give you an example: Review: My cat won't touch these. My dog, however, chews them and makes a mess all over the carpet and I can't get the shredded sticks out! Messy. Waste of money!
Summary: Cat hates them
The answer to this example can be: True
Here is why: The answer is True. Because it's a correct summary where the owner mentioned their cat hated the product.
OK. solve this:
Reviews: The ice coffee setting does not work properly. It barely puts out enough coffee for a shot glass reguardless of the serving size it is set on. The regular and rich brew setting works great.
Summary: Great idea and so happy they offer these but not ...
Answer: | False | 8 | NIv2 | task1309_amazonreview_summary_classification | fs_opt | [
-0.447592556476593,
-0.10233774781227112,
0.017615145072340965,
-0.15839172899723053,
0.10936447978019714,
-0.68672776222229,
0.1298442780971527,
0.8467467427253723,
-0.46198558807373047,
0.29976409673690796,
-0.2530253529548645,
-0.2707953155040741,
-0.3988472819328308,
-0.025819066911935... |
You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Italian.
One example is below.
Q: "" אף אדם אינו אי העומד בפני עצמו.
A: "" Nessun uomo è un'isola completamente a sé.
Rationale: The Hebrew sentence is correctly translated into Italian, because the meaning is preserved.
Q: באמנויות משתמשים בניתוח גם כן.
A: | Usano anche l'analisi. | 9 | NIv2 | task1111_ted_translation_he_it | fs_opt | [
-0.2303788959980011,
0.5492770671844482,
-0.18696939945220947,
-0.04730644077062607,
-0.0533595010638237,
-0.9691639542579651,
0.9755045175552368,
0.10770032554864883,
0.14409248530864716,
-0.6054442524909973,
-0.6661219596862793,
0.2878129184246063,
-0.8101253509521484,
0.4348757863044739... |
You are given a statement written in Hindi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .
Example Input: Statement: विश्व के सभी प्रमुख देशों में कण त्वरक बनाये गये हैं। इस समय विश्व के विभिन्न देशों में विभिन्न प्रकार के, विभिन्न उर्जा वाले एवं विभिन्न उपयोग के लिये निर्मित कई हजार कण त्वरक हैं। <MASK> स्थित सर्न (CERN) लार्ज हैड्रान कोलाइडर विश्व का सबसे विशाल और शक्तिशाली कण त्वरक है।
Option A: सर्न
Option B: जेनेवा
Option C: कोलकाता
Option D: स्प्रिंग-८
Example Output: जेनेवा
Example Input: Statement: होम रेंज की सीमा पूर्ण रूप से शिकार करने की उपलब्धता पर निर्भर करता है। दक्षिणी अफ्रीकी वुडलैंड में चीते की सीमा कम से कम जबकि <MASK> के कुछ भागों में तक पहुंच सकते हैं।
Option A: ड्यूमा
Option B: इथोपिया
Option C: अंगोला
Option D: नामीबिया
Example Output: नामीबिया
Example Input: Statement: वेद प्रताप वैदिक का जन्म 30 दिसम्बर 1944 को <MASK> में हुआ। वे सदैव प्रथम श्रेणी के छात्र रहे। दर्शन और राजनीति उनके मुख्य विषय थे। उन्होंने जवाहरलाल नेहरू विश्वविद्यालय से अन्तरराष्ट्रीय राजनीति में पीएचडी करने के पश्चात् कुछ समय दिल्ली में राजनीति शास्त्र का अध्यापन भी किया।
Option A: काबुल
Option B: हाथरस
Option C: मास्को
Option D: इंदौर
Example Output: | इंदौर
| 3 | NIv2 | task947_wiki_cloze_hi_multiple_choice_question_answering | fs_opt | [
1.0391478538513184,
1.117958903312683,
-0.1626971811056137,
0.31246089935302734,
0.10119184851646423,
-0.3562330901622772,
-0.030428394675254822,
0.6695115566253662,
-0.11876076459884644,
0.03937724977731705,
-0.0732249915599823,
0.6797840595245361,
-0.9872913360595703,
-0.4001034498214721... |
Given the task definition and input, reply with output. You will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For simplicity, answers should be in all lower cased letters.
Category: THE UNITED STATES OF MEXICO
Clue: From the Arabic Wadi Al-Hijarah, it's Mexico's second-largest city
| guadalajara | 5 | NIv2 | task306_jeopardy_answer_generation_double | zs_opt | [
-0.8386073112487793,
0.44034603238105774,
0.02301040291786194,
-0.2657272517681122,
-0.2249225378036499,
0.5984313488006592,
0.7130534648895264,
0.30397915840148926,
0.27065861225128174,
-0.005018654745072126,
-0.40828409790992737,
-0.49410322308540344,
-0.500885009765625,
-0.0749756395816... |
In this task you are given a sentence. You must judge whether the main verb of the sentence is in present or past tense. Label the instances as "Present" or "Past" based on your judgment. If there is no verb in the given text, answer "Present".
[EX Q]: So much blood, too much for the baby, a boy she named Charles Edwin.
[EX A]: Past
[EX Q]: Twelve Thirty hopped and clapped his moustache together in excitement.
[EX A]: Past
[EX Q]: the woman screeched and stomped back over to where she had dropped the gnome.
[EX A]: | Past
| 6 | NIv2 | task429_senteval_tense | fs_opt | [
-0.19235306978225708,
0.4577418863773346,
0.02221990004181862,
-0.13313135504722595,
-0.146352618932724,
-0.3087666630744934,
0.7942889928817749,
0.8674466013908386,
0.4444766044616699,
-0.20600998401641846,
-0.5501757264137268,
0.4035637378692627,
-0.5795157551765442,
-0.3033435344696045,... |
Q: A text is given in Bengali. Translate it from the Bengali language to the Gujarati language. The translation must not omit or add information to the original sentence.
এর আগে প্রধানমন্ত্রী তালকোটরা স্টেডিয়ামে ক্রিডাই আয়োজিত এক প্রদর্শনীও ঘুরে দেখেন।
A: | અગાઉ પ્રધાનમંત્રીએ તાલકટોરા સ્ટેડિયમમાં ક્રેડાઈ દ્વારા આયોજિત પ્રદર્શનની મુલાકાત લીધી હતી. | 7 | NIv2 | task1067_pib_translation_bengali_gujarati | zs_opt | [
0.37874501943588257,
0.3312336504459381,
-0.33579742908477783,
-0.14995500445365906,
0.1627887785434723,
-0.7560763359069824,
-0.26998257637023926,
-0.740359365940094,
0.20135048031806946,
-0.14549337327480316,
-0.7619056105613708,
-0.2249094694852829,
-0.23332399129867554,
0.8625271916389... |
In this task, you are presented with a term, a description of the term, and an expected answer ('yes' or 'no'). You should write a yes-no question about the given term such that the answer is the one provided to you (i.e., If the answer is "No", you should ask a question that its answer would be "No", and if the answer is "Yes", you should ask a question that its answer is "Yes". ). The question should have a definitive answer (as opposed to ambiguous or subjective questions, e.g., Is Batman a good movie?). Create a question such that its answer can not be found easily on a single web page (e.g., mentioned in a Wikipedia page). This can be accomplished if answering the question requires more than one fact (facts = statements that can be found on a Wikipedia page or Google). For example, answering the question 'did Aristotle use a laptop?', one needs the know about the invention of the laptop and the death of Aristotle. Avoid questions should not just compare the properties of objects (e.g., Is a door bigger than an elephant?) or those that refer to details in the given description.
Q: Term: Indigenous peoples in Canada, Description: North American indigenous peoples within the boundaries of present-day Canada, Answer:Yes
A: | Do the Indigenous people in Canada reside in the United States? | 4 | NIv2 | task167_strategyqa_question_generation | zs_opt | [
0.8100402355194092,
-0.05735846236348152,
-0.35463809967041016,
0.4816950559616089,
-0.5606392621994019,
-0.20669952034950256,
1.0049556493759155,
0.5938012599945068,
0.037424229085445404,
-0.12964048981666565,
-0.015057571232318878,
0.4743807911872864,
-0.5818700790405273,
-0.484289348125... |
Given a document and an entity the task is to select the author's sentiment towards the entity. Sentiments can be Positive, Neutral and Negative. Select Positive if the article expresses a positive view towards the given entity or praises its quality or skills. Select Neutral if the document expresses no clear view towards the entity or has equal amounts of positive and negative statements or expressing some fact/quote by someone else. Select Negative if the article expresses a negative view towards like harsh remarks, criticizing entities action/decision etc. Note that URLs in the text have been replaced with [Link].
What is the sentiment of the following document towards the entity Bashar al-Assad ? “I support Assad because he 's the defender of Middle Eastern Christianity " one member of the alt-right tells BuzzFeed News giving just one reason why he and others like him back the Syrian president.
The brutal leader at the center of Syria’s five-year-long war has found support in one of the least likely places — among the alt-right. The white nationalists and trolls who identify with the alt-right have lifted up Bashar al-Assad as a hero in recent years. Support for the Syrian president means they can further tangled internet conspiracy theories taps into a deep vein of anti-Semitism anti-interventionism and anti-globalism and allows them to wind up their biggest enemy: liberals. It was a love affair years in the making. The nationalistic fervor that the Syrian government whipped up in its propaganda over the years has found a home in the hearts of many on the alt-right the Intercept reports. From the point of view of James Alex Fields Jr. — who posted a popular meme of Assad on his Facebook profile before being charged with the death of a counterprotester in Charlottesville Virginia last month — and others like him Assad was a figurehead who symbolized rebellion a rejection of the popularly accepted narrative. He was also the perfect way to troll liberals like the ones Fields was marching against in Charlottesville. As Ben Nimmo of the Atlantic Council’s Digital Forensic Research Lab put it the simplest explanation of the alt-right’s support for Assad is “the principle of ‘my enemy’s enemy’” — meaning mainstream media and politicians. “ Assad has been repeatedly condemned by mainstream politicians especially Democrats and the mainstream media ” Nimmo told BuzzFeed News. “The alt-right forged their identity around demonizing the Democrats and the mainstream media. Amplifying or supporting Assad is therefore a way for the alt-right to troll their enemies.”
" Assad did nothing wrong " the man yells. "Support the Syrian Arab Army." In the background another man chimes in: " Assad is the man!"
" Assad did nothing wrong" - Baked Alaska at UVA tonight. "Barrel bombs hell yeah!"
The protests in Charlottesville culminated in violence and the death of a young female counterprotester Heather Heyer. In the days after her killing a pro- Assad meme showing the Syrian leader dressed in military fatigues wearing sunglasses and with the word “undefeated” at the bottom was found on Fields' Facebook page.
People who fall in the center of the Venn diagram of Assad backers and Trump fans contacted in the aftermath including both devoted members of the alt-right movement and those who have disavowed it said they had been pro- Assad before being pro-Trump. Many said they believed that Assad would protect Syria’s Christians after pro-democracy protests morphed into a civil war following the government’s brutal crackdown. Lue-Yee Tsang an alt-right supporter in his late twenties who lives in the DC area said he supported a president who protected and “supported the right of peaceful groups to maintain their ways of life ” as he believes Assad did. When the US election came around Trump was the only candidate he considered supporting. “I’d love to have a Christian emperor instead but given the field he was the best there was ” he said. A far right nationalist who goes by the Twitter handle @IWillRedPillYou who supports the expression of the alt-right’s views and who declined to give their real name put it simply: “I support Assad because he 's the defender of Middle Eastern Christianity.”
Bashar al Assad is a hero. The protector of Christians in the Middle East.
An estimated million Christians are among the 6 million people who have been displaced inside Syria or fled the country entirely among intense fighting while others are reported to have fled to regime-held areas and generally support the regime. Many were targeted by ISIS who began operating in the country in 2014 further compounding the violence of the civil war. Some alt-right supporters said their love for Assad was also a means of advocating for American non-intervention a facet they share with some left-wing supporters of Assad 's regime. But they also stress the need to fight ISIS — the alt-right has repeatedly trumpeted the threat that radical Islamic terror poses to America and the west generally. In Assad many on the far and alt-right see the Syrian leader holding a “crucial foothold” against larger geopolitical forces Alexander Reid Ross author of the new book Against the Fascist Creep and a lecturer of geography at Portland State University told The Intercept. Assad ’s actions would contain Islamic terror but (crucially) wouldn’t involve American forces. But more than that those who spoke to BuzzFeed News were convinced that the Syrian war wasn’t simply a case of citizens agitating for freedom from a repressive regime. What they saw was Israel and the so-called “deep state” hard at work to disrupt a country that's just trying to protect itself. (The “deep state” refers to the myriad intelligence agencies and establishment officials they believe really run the US at the expense of the people.) What that meant they said was that Assad wasn’t the villain — he was the hero. “Without Assad Muslims would conquer and likely decimate those remaining Christians ” user @IWillRedPillYou said. If anything Assad ’s faith as part of a minority Muslim sect in Syria — albeit a hugely powerful one — was yet another a reason to support him. And he said the Syrian dictator was a “sovereign leader that's been targeted by Zionist expansion for the better part of a decade.” “Even those who know very little about Assad see [being pro- Assad ] as part of a culture of opposition to both Daesh and the Jewish state of Israel ” Tsang who stated he was “not anti-Muslim at all ” said. “I mean it’s all over the memes so it’s easy to pick up culturally.” User @IWillRedPillYou claimed that Israel wished to take part of Syria in the Golan Heights while Iran’s involvement in the conflict was due to a desire to push back against Israel. “ Bashar al-Assad is caught in the midst of fighting both ” they said. “ Bashar al-Assad did nothing wrong.” Such beliefs Nimmo noted were reflective of the alt-right’s “very strong preference for conspiracy theories” and their “abiding belief in the ‘Deep State’ and ‘neocon’ conspiracies to hold onto power against The Will Of The People.” The focus on Israel mirrored their focus on Jews in the US.
It appeared to begin with a hashtag that appeared earlier that year #CantMossadTheAssad which had its first mentions on Twitter from very small accounts with fewer than 100 followers each. The hashtag itself played into the recurring anti-Semitic theme among many in the alt-right — that Israel’s intelligence and security agency was running the show in Syria. In August 2013 Alex Jones of Infowars ran an interview with a pro- Assad blogger named Mimi Al-Laham better known as PartisanGirl but who also goes by a host of online names. Al-Laham told Jones it was implausible that the Syrian government had staged the chemical attack which killed hundreds of people including children and was documented by extensive video evidence. The US the UK and France all said in September following a UN report that they believed only the Syrian government was behind the attack. But almost immediately after the videos of the attack began spreading on Twitter supporters of Assad — from alt-right trolls to the Russian government — said there was no way the Assad regime could be involved. Jones also ran with it and said the operation was a “false flag ” an event staged to spark a reaction blaming the attack on the rebels and claiming the war itself was part of a movement orchestrated by Goldman Sachs and Israel. Those in the alt-right appear to see no issue in cheerleading for a Muslim leader while simultaneously agitating against Islam. So Richard Spencer who first helped popularize the term “alt-right ” is able to aggressively support Trump’s “Muslim ban ” while also getting behind the Syrian dictator because as he told BuzzFeed News Assad had been “educated in the West and offer[ed] a civilized variant of Islam.” “ He was educated in Britain so was his wife he just seems to be a reasonable person ” he said. “I have more sympathy to some leaders because I feel I share something with them. I do like him more. His wife is very beautiful and a sophisticated woman as well.”
The #AltRight backs Assad .
Spencer said he ’d been “aware” of Assad since the early 2000s. Coverage of Assad at the time soon after he ’d inherited the presidency from his father was limited to a rigged referendum confirming his succession ( he was the only candidate) and muted support for an opening up of the tightly controlled state.
The core of it for Spencer was that Assad in addition to being the “rightful legitimate ruler of Syria ” was fighting ISIS. Harking back to the question of his support for an Islamic leader Spencer stated: “The question really isn’t do I support white people or Assad the question really is whether I support Assad or ISIS?” But the alt-right narrative was complicated by the 2017 chemical attack on Khan Sheikhoun in Idlib province which Trump responded to by launching a series of airstrikes into Syria — the first time the US had targeted the regime in all its years of smaller-scale involvement. The strikes provoked a split in prominent alt-right media figures between those who continued to support Trump and those who officially declared themselves “OFF the Trump train ” in the case of British citizen Paul Joseph Watson. (He would later recant and rejoin the train.)
Those in the alt-right who supported Assad prior to supporting Trump came to see the US president’s strikes as explicit evidence of the deep state’s interference in Syria with Mike Cernovich at the time a leading alt-right personality leading the charge by amplifying the #SyriaHoax false flag — laying the blame squarely at the feet of the “deep state.” As Spencer put it: “The fact that I and most all of the alt-right offer him moral support is because he has become a bogeyman in the mainstream media and is clearly the target of the Deep State military industrial complex foreign-policy establishment.” “Sure there might be some kids out there who want to shock their parents with an Assad meme or something like that ” he admitted putting those individuals on one end of a “spectrum” of support for the Syrian leader. Many of those in the alt-right who support Assad are situated somewhere in the middle of reactionary trolling and deep state theories according to Spencer . “There are a lot of people who are so skeptical of everything that Washington does that whenever Assad is in the crosshairs they don’t like it even if they don’t quite understand the full complexity of the issue.” He continued: “But I imagine that on the whole most in the alt-right share my perspective.” The engagement of a mostly younger internet-literate crowd — like Tsang — rests on an bedrock of older and more traditional right-wing and far-right support for the Syrian president. David Duke former imperial wizard of the Ku Klux Klan has voiced his support for Assad as has Ann Coulter. Across the Atlantic France’s Marine Le Pen has stated that Assad is the the “solution” to the region’s current turmoil and in the UK Nigel Farage has voiced tepid support for the continuation of the Assad regime as has controversial columnist Katie Hopkins British Infowars writer Watson and British Nationalist Party founder Tommy Robinson. But Cernovich wants everyone to ignore the memes the support at Charlottesville the discussions online — and his once-upon-a-time advocacy for Assad . As Cernovich attempts to join the mainstream he is pivoting away from some tenets — such as support for Assad — and despite evidence to the contrary arguing that such support does not exist. Despite that he does think the Syrian leader should remain in place: “Opposing regime change in my view isn’t supporting anyone.” “Zero Trump supporters back Assad this is the definition of fake news ” he said. “I've talked to thousands of Trump supporters never heard of Assad support.” ● | Positive | 0 | NIv2 | task420_persent_document_sentiment_classification | zs_opt | [
0.351266086101532,
0.10381569713354111,
-0.29287397861480713,
0.12485954165458679,
0.4996282458305359,
-0.37072044610977173,
1.2258682250976562,
0.8196024894714355,
0.38999974727630615,
0.8270431756973267,
-0.14925390481948853,
0.25292354822158813,
-0.264829158782959,
-0.2117207646369934,
... |
In this task, you are given a tuple, comprising Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonY or others will be affected as mentioned in the Tail or not. These effects are social actions that may occur after the Head event. For example, X may get hugged, and Y may blush in response. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
One example: Head: PersonX goes the way of the dodo<sep>Tail: none
Solution is here: Yes
Explanation: This is a good example. As a result of the Head, others won't be affected.
Now, solve this: Head: PersonX bears ___ unto the PersonY<sep>Tail: commanding
Solution: | No | 6 | NIv2 | task1196_atomic_classification_oeffect | fs_opt | [
0.448166161775589,
0.2650246024131775,
0.4064773917198181,
-0.12069473415613174,
-0.2607736587524414,
-1.1281269788742065,
0.5603553056716919,
0.8737884759902954,
-0.2029457688331604,
-0.4431661367416382,
-0.635554313659668,
-0.17539842426776886,
-0.6210522651672363,
-0.31822913885116577,
... |
Teacher:In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether it is plausible for the Head to desire the Tail or not. In this task, desire means desires of sentient entities. For example, doctors likely desire to cure a patient. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Teacher: Now, understand the problem? Solve this instance: Head: PersonX asks PersonY's grandma<sep>Tail: Check how Person Y's grandma responds
Student: | No | 6 | NIv2 | task1213_atomic_classification_desires | zs_opt | [
0.001168718095868826,
0.0827755331993103,
0.3856446444988251,
-0.4369955062866211,
-0.5803513526916504,
-0.5646638870239258,
1.232933521270752,
0.3394068479537964,
-0.2195412516593933,
-0.5072779655456543,
-0.16946351528167725,
-0.21994546055793762,
-0.5716196298599243,
0.3921658396720886,... |
Given a sentence in Korean, provide an equivalent paraphrased translation in French that retains the same meaning both through the translation and the paraphrase.
Q: 1923 년에 독립적 인 일원 인 John Archibald Maharg가 야당의 지도자로, 1924 년과 1925 년에 Harris Turner가 독립적으로 야당 지도자로 봉사했습니다.
A: | En 1923, John Archibald Maharg était un membre indépendant du chef de l'opposition et Harris Turner, également indépendant, avait servi de chef de l'opposition en 1924 et 1925. | 4 | NIv2 | task784_pawsx_korean_french_translation | zs_opt | [
0.012966420501470566,
0.062179647386074066,
-0.7328806519508362,
0.11813133955001831,
0.049206942319869995,
-1.394273042678833,
1.166609287261963,
-0.7454235553741455,
-0.6259004473686218,
0.16886667907238007,
-0.18154318630695343,
-0.10155225545167923,
-0.6859295964241028,
0.1489503681659... |
You will be given a definition of a task first, then some input of the task.
In this task, you are given four sentences: a bot task sentence, a bot role sentence, a user task sentence and a user role sentence. Your job is to classify given sentences into one of the 47 different domains. The domains are: 'UPDATE_CALENDAR', 'PRESENT_IDEAS', 'MOVIE_LISTINGS', 'AUTO_SORT', 'GAME_RULES', 'CONTACT_MANAGER', 'BANK_BOT', 'MUSIC_SUGGESTER', 'CHECK_STATUS', 'PET_ADVICE', 'HOW_TO_BASIC', 'NAME_SUGGESTER', 'QUOTE_OF_THE_DAY_BOT', 'GUINESS_CHECK', 'INSURANCE', 'RESTAURANT_PICKER', 'MAKE_RESTAURANT_RESERVATIONS', 'WEDDING_PLANNER', 'SKI_BOT', 'HOME_BOT', 'PLAY_TIMES', 'BUS_SCHEDULE_BOT', 'WHAT_IS_IT', 'PHONE_PLAN_BOT', 'DECIDER_BOT', 'PHONE_SETTINGS', 'TIME_ZONE', 'LIBRARY_REQUEST', 'UPDATE_CONTACT', 'CATALOGUE_BOT', 'PROMPT_GENERATOR', 'SCAM_LOOKUP', 'SPORTS_INFO', 'POLICY_BOT', 'CITY_INFO', 'APARTMENT_FINDER', 'EVENT_RESERVE', 'SHOPPING', 'EDIT_PLAYLIST', 'LOOK_UP_INFO', 'ORDER_PIZZA', 'WEATHER_CHECK', 'APPOINTMENT_REMINDER', 'GEOGRAPHY', 'STORE_DETAILS', 'AGREEMENT_BOT', 'ALARM_SET'.
Bot's task: Inform the user that the store does not give refunds or accept returned goods
Bot's role: You are a bot designed to help customers order products from a store's website
User's task: You want to return a defective bicycle helmet to a sporting goods website. If the bot refuses to refund you, argue with it
User's role: You are interacting with a bot designed to help you order products from a store's website
Output: | SHOPPING | 1 | NIv2 | task1394_meta_woz_task_classification | zs_opt | [
0.4193686246871948,
-0.23582583665847778,
-0.5022392868995667,
0.49994561076164246,
0.50440514087677,
-0.08036462962627411,
0.5257769227027893,
0.2927519977092743,
0.12013446539640427,
0.12231215089559555,
-0.36241498589515686,
0.4717518985271454,
-0.09171026945114136,
-0.02887710556387901... |
instruction:
In this task, you are given a sentence in the English language and your task is to convert it into the Japanese language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).
question:
"Twitter is depriving cyberdissidents in repressive countries of a crucial tool for information and organization."
answer:
「ツイッターは、抑圧的な国々において、情報と組織のための重要なツールを反体制派から奪う」
question:
Many people, such as retired and serving military officials, civilians, had come to the bank to collect their salaries, were killed or wounded by the blast.
answer:
退役および現役の軍当局者達や一般市民らなど、多くの人々が彼らの給与を取りに銀行に来ており、その爆発によって殺害もしくは負傷させられた。
question:
They went from being behind 14-8 to being down 20-17; at which point, Ukraine took a time out.
answer:
| 彼らは、14対8と遅れを取った時から、20対17になるまで試合を続け、その時点で、ウクライナがタイムアウトを取った。
| 9 | NIv2 | task435_alt_en_ja_translation | fs_opt | [
-0.5588034391403198,
0.21843086183071136,
0.24145665764808655,
-0.5058939456939697,
0.16405335068702698,
-0.5014178156852722,
1.221191167831421,
0.4225008487701416,
0.47803783416748047,
0.09514135122299194,
-0.2918381989002228,
0.014539922587573528,
-0.8487439751625061,
0.11260753124952316... |
Q: In this task you will be given a list of integers. You should remove all of the integers that are divisible by 3 from the list. If every integer in the input list is divisible by 3 then an empty list should be returned. Zero is divisible by 3.
[89, 17, 38, -43, 68, -19, 98, 8, 69, -76]
A: | [89, 17, 38, -43, 68, -19, 98, 8, -76] | 7 | NIv2 | task370_synthetic_remove_divisible_by_3 | zs_opt | [
0.3402710556983948,
-0.09904313087463379,
-0.7639422416687012,
-1.0190130472183228,
0.14596593379974365,
0.3845650553703308,
1.4238059520721436,
-0.2865850627422333,
-0.5019261837005615,
0.006722697056829929,
-0.7258466482162476,
0.24473774433135986,
0.004101631231606007,
-0.44178810715675... |
You will be given a definition of a task first, then some input of the task.
In this task, you will be presented with a text, a pronoun from the text, and two candidate names. You should determine what the pronoun refers to and classify the answers into A, B, or Neither. A and B here are referring to option A and option B. Position of the pronoun in the text is showed within two "_"s.
In Episode 7, she befriends an ``Alice'' (monster who resembles a human maid) but sadly she meets a tragic end because of the actions of Zealotus (a half monster who despises humans) in Episode 19. In their final confrontation in Comodo, Maya nearly kills Jiltus for revenge but Alice's spirit comes to Maya and convinces _her_ to forgive Zealotus. <sep>, Pronoun: her <sep>, A: Alice <sep>, B: Maya
Output: | B | 1 | NIv2 | task329_gap_classification | zs_opt | [
-0.11698415130376816,
0.23664918541908264,
0.2752262055873871,
0.07644864916801453,
-0.1686915010213852,
-0.030041657388210297,
0.8855442404747009,
0.4867056608200073,
0.2521514892578125,
0.27180781960487366,
-0.13270097970962524,
-0.5548102855682373,
0.3257215619087219,
-0.290609896183013... |
Given the task definition and input, reply with output. In this task, you are given a sentence in the Hindi language and a corresponding English translation of the Hindi sentence. Your task is to generate a label "Yes" if the translation is correct, otherwise generate label "No". In the translation, English sentence should preserve the number as it is and it should be in sentence case (capitalize only the first word of each sentence and noun).
Hindi: ब्रिटिश भारत तथा देसी रियासतों के प्रतिनिधियों को इस समिति के सामने गवाह के रूप में साक्ष्य देने के लिए आमंत्रित किया गया था ।
English: Representatives of British India and of the Princely States were invited to give evidence before the Committee as witnesses .
| Yes | 5 | NIv2 | task426_hindienglish_corpora_hi-en_classification | zs_opt | [
-0.27148863673210144,
0.6311554908752441,
0.7132924795150757,
0.1099223792552948,
-0.019848965108394623,
-0.8955934047698975,
0.30661171674728394,
0.2957967221736908,
-0.3997874855995178,
-0.3470091223716736,
-0.42600563168525696,
0.8470228910446167,
-0.3112115263938904,
0.2411249577999115... |
You are given a math word problem and you are supposed to make use of mathematical concepts like probability, combinatorics, linear equations, sequences/series, or simple operators like addition, subtraction, division, or multiplication to answer the given question. Choose the best option from the 5 given options and report that option.
Q: Question: When n liters of fuel was added to a tank that was already 1/3 full, the tank was filled to 5/9 of its capacity. In terms of n, what is the capacity of the tank, in liters?
Option A: 10/9 n
Option B: 4/3 n
Option C: 9/2 n
Option D: 9/4 n
Option E: 7/3n
A: | Option C | 4 | NIv2 | task750_aqua_multiple_choice_answering | zs_opt | [
0.649641752243042,
0.1662450134754181,
0.02817603573203087,
-0.09375066310167313,
-0.10288096964359283,
-0.7819442749023438,
0.5691853165626526,
0.8457125425338745,
-0.11996114999055862,
0.42622125148773193,
-0.8324410915374756,
-0.6366851329803467,
-0.6079605221748352,
-0.0011736275628209... |
Detailed Instructions: In this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.
See one example below:
Problem: Sentence1: 'a red bus goes down the street beside a yellow building', Sentence2: 'the colorfully decorated living room has a retro style chair in it'. Is the frequency of the word 'beside' in two sentences equal?
Solution: No
Explanation: Frequency of the word 'beside' in Sentence1 is 1 but 0 in Sentence2. So, the answer is 'No'
Problem: Sentence1: 'a bunch of clocks and some pictures on a table of some sort', Sentence2: 'young school boys smiling and posing on a stone wall'. Is the frequency of the word 'a' in two sentences equal?
Solution: | No | 4 | NIv2 | task159_check_frequency_of_words_in_sentence_pair | fs_opt | [
-0.32830867171287537,
0.6622723340988159,
-0.28342804312705994,
0.08402760326862335,
0.17074240744113922,
-0.31534457206726074,
0.12125392258167267,
1.2925586700439453,
0.285667359828949,
0.1071881502866745,
-0.4998646676540375,
-0.2469230443239212,
0.43875277042388916,
0.01810305006802082... |
You are given a math word problem and you are supposed to make use of mathematical concepts like probability, combinatorics, linear equations, sequences/series, or simple operators like addition, subtraction, division, or multiplication to answer the given question. Choose the best option from the 5 given options and report that option.
[EX Q]: Question: There are 4 boys and 3 girls seated in a row.Find the probability that all girls are together?
Option A: 1/6
Option B: 1/7
Option C: 2/7
Option D: 3/7
Option E: 4/7
[EX A]: Option B
[EX Q]: Question: Two stations A and B are 20 km apart on a straight line. One train starts from A at 7 a.m. and travels towards B at 20 kmph. Another train starts from B at 8 a.m. and travels towards A at a speed of 25 kmph. At what time will they meet?
Option A: 9
Option B: 10
Option C: 11
Option D: 12
Option E: 8
[EX A]: Option E
[EX Q]: Question: The speed at which a man can row a boat in still water is 6 km/hr. If he rows downstream, where the speed of current is 3 km/hr, how many seconds will he take to cover 80 meters?
Option A: 28
Option B: 32
Option C: 36
Option D: 40
Option E: 44
[EX A]: | Option B
| 6 | NIv2 | task750_aqua_multiple_choice_answering | fs_opt | [
1.0203295946121216,
-0.3132728934288025,
-0.5887848138809204,
-0.8253114223480225,
0.3835234045982361,
-0.2891756296157837,
0.6592879295349121,
0.7071398496627808,
-0.13788558542728424,
-0.42869457602500916,
-0.4685547947883606,
0.2650905251502991,
0.03798775374889374,
0.07138276100158691,... |
You are given a sentence in Spanish. Your job is to translate the Spanish sentence into English.
One example is below.
Q: Con el crecimiento, los países y las sociedades ingresan en un ciclo virtuoso de movilidad ascendente, de oportunidad y mejores niveles de vida.
A: With economic growth, countries and societies enter into a virtuous cycle of upward mobility, opportunity and improved living standards.
Rationale: The Spanish sentence is correctly translated into English, because the meaning is preserved.
Q: Lo estás haciendo por la tarea en sí, por el reto — y el océano es el entorno más desafiante que hay, por la emoción del descubrimiento, y por ese extraño vinculo que nace cuando un pequeño grupo de gente forma un equipo muy unido.
A: | You're doing it for the task itself, for the challenge — and the ocean is the most challenging environment there is — for the thrill of discovery, and for that strange bond that happens when a small group of people form a tightly knit team. | 9 | NIv2 | task1226_ted_translation_es_en | fs_opt | [
-0.9176205396652222,
0.9630066156387329,
0.26173096895217896,
-0.26433005928993225,
-0.14462906122207642,
-0.08929990977048874,
-0.07933347672224045,
0.8964986801147461,
0.05816198140382767,
-0.4154377281665802,
-0.19922009110450745,
0.19476842880249023,
-0.8244075775146484,
-0.13849881291... |
In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A after the first i elements. i will always have a value less than the length of A.
One example: 3, ['a', '34', 'f', '931', '7', '3432', '13245', '762']
Solution is here: 931, 7, 3432, 13245, 762
Explanation: Here, all the elements except the first 3 from the list are '931', '7', '3432', '13245', and '762'.
Now, solve this: 2, ['e', '3339', 'J', 'J', '2115', 'c', '8843', 'q', 'd']
Solution: | J, J, 2115, c, 8843, q, d | 6 | NIv2 | task064_all_elements_except_first_i | fs_opt | [
-0.09952018409967422,
0.5866392254829407,
-0.42258667945861816,
-0.7990080714225769,
-0.4439343810081482,
-0.09734185039997101,
0.9515491127967834,
0.0011206148192286491,
-0.5063222646713257,
-0.20016390085220337,
-0.7177817225456238,
-0.10619091242551804,
-0.11866310238838196,
-0.33968102... |
Part 1. Definition
You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Hebrew.
Part 2. Example
ويمكن اعادة تكرار هذه العملية على طول الشريط لكي نطبق شريط الحمض النووي فنشكل ما يشبه المستطيلات
Answer: סך כל הפעולות של המהדקים על הגדיל הארוך מקפלות אותו לצורה דמויית מלבן.
Explanation: The Arabic sentence is correctly translated into Hebrew, because the meaning is preserved.
Part 3. Exercise
(مارتن): موضوعي في هذا الكتاب أن هناك سبعة مليار شخص في هذا العالم وهناك في الواقع سبعة مليارات طريقة مختلفة يمكن للمرء من خلالها التعبير عن جنسه
Answer: | מ "" ר: התיזה שלי בספר הזה היא שיש שבעה מיליארד אנשים בעולם, ולמעשה, שבע מיליארד דרכים יחודיות להביע את המגדר של מישהו. | 7 | NIv2 | task1233_ted_translation_ar_he | fs_opt | [
-0.32986992597579956,
0.5920054316520691,
-0.07176672667264938,
-0.5476434230804443,
-0.18979567289352417,
0.23514874279499054,
1.283782720565796,
-0.46027979254722595,
0.6764456629753113,
-0.47822970151901245,
-1.2140581607818604,
0.06929197907447815,
-0.829812228679657,
-0.00569781940430... |
Definition: You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Farsi.
Input: אבל פה, משלמי המיסים מכסים את החשבון ומה שהילדים מקבלים זה תא כלא קר וסימן תמידי נגדם כשהם מגיעים הביתה וניגשים לקבל עבודה.
Output: | اما در اینجا مالیات دهندگان هزینه آن را می پردازند و یک سلول سرد آن چیزی است که نوجوانان می گیرند و سابقه ای که هنگام برگشت به خانه و درخواست شغل همیشه همراهشان هست. | 2 | NIv2 | task1113_ted_translation_he_fa | zs_opt | [
-0.14379814267158508,
0.28382664918899536,
-0.6903829574584961,
-0.3853249251842499,
-0.7110028266906738,
0.19346074759960175,
0.661884069442749,
0.5826849341392517,
0.5979100465774536,
0.33577054738998413,
-0.6287721395492554,
0.11817623674869537,
-0.5804812908172607,
0.3777363896369934,
... |
In this task, you are given a hateful post in Bengali that expresses hate or encourages violence towards a person or a group based on the protected characteristics such as race, religion, sex, and sexual orientation. You are expected to classify the post into four classes: Religious, Political, Geopolitical and Personal depending on the topic.
করো । হাজার হাজারকেতো মেরে ফেলেছ প্রয়োজনে আরো মার শুধু মাত্র আমাদের বাংলাদেশে তাদের আসতে দিয়োনা । এটাই কি আসল মতলব । এমন অমানবতা সুলভ কথা আমার মনপুতঃ নয় । বরং এক্ষুনি তাদের জীবন রক্ষার্থে আশ্রয় শিবিরের ব্যবস্হা করুন এবং তাদের সম্পূর্ণ নিরাপত্তার ব্যবস্হা নিশ্চিত করেই তাদের আন্তর্জাতিক সংস্থা জাতিসংঘ বা ইউরোপিয় ইউনি য়ন ইত্যাদির মধ্ | Political | 0 | NIv2 | task1494_bengali_hate_speech_classification | zs_opt | [
-0.23051536083221436,
0.2557888627052307,
0.11893485486507416,
0.40942370891571045,
-0.3307076394557953,
-0.3390973210334778,
0.07180802524089813,
0.15088146924972534,
-0.5711787939071655,
0.1248321682214737,
-0.4883151054382324,
-0.3100140690803528,
0.12058885395526886,
-0.432924896478652... |
In this task, you will be given a passage consisting of set of facts. The task is to create a question of form 'Where is <person_name>?' that is answerable from exactly one of the given facts. Avoid creating questions that are unanswerable from all of the facts.
Passage: Daniel went back to the office. Sandra went to the garden. John journeyed to the bedroom. Mary went back to the bathroom. | Where is Sandra? | 0 | NIv2 | task082_babi_t1_single_supporting_fact_question_generation | zs_opt | [
0.24189375340938568,
0.9428308010101318,
-0.8077095746994019,
-0.41368091106414795,
-0.49699366092681885,
-0.4507191777229309,
0.866478681564331,
0.03620448336005211,
0.19280973076820374,
0.029917778447270393,
-0.3388884663581848,
0.38891929388046265,
-0.159187912940979,
0.1854023635387420... |
Detailed Instructions: A text is given in English. Translate it from the English language to the Oriya language. The translation must not omit or add information to the original sentence.
Q: However, the expenditure would continue to be monitored at National Level within the prescribed ceiling. It will help the States in positioning and training of requisite manpower for better implementation of the mission.
A: | ନିଜର ପ୍ରାରମ୍ଭିକ ଅଭିଭାଷଣକୁ ଉଲ୍ଲେଖ କରି ପ୍ରଧାନମନ୍ତ୍ରୀ କହିଥିଲେ ଯେ ଅତ୍ୟନ୍ତ ସରଳ ଭାବେ ସେ ନୂଆ ଭାରତ(New India)ର ଦୃଷ୍ଟିଭଙ୍ଗୀ ଓ 5ହଜାର ବର୍ଷ ପୂର୍ବେ ଲେଖାଯାଇଥିବା ବେଦ ସମ୍ପର୍କରେ କହିଥିଲେ । ବେଦରେ କୁହାଯାଇଛି ଯେ ପ୍ରକୃତିର ଦୋହନ କରାଯାଇପାରିବ କିନ୍ତୁ ପ୍ରକୃତିର ଶୋଷଣ ନୁହେଁ । | 9 | NIv2 | task987_pib_translation_english_oriya | zs_opt | [
-0.42341387271881104,
0.33561453223228455,
-0.27285391092300415,
-0.23438140749931335,
0.37784188985824585,
-1.1497318744659424,
1.0548943281173706,
0.42519962787628174,
-0.494393527507782,
0.38392651081085205,
-0.39009541273117065,
-0.35840463638305664,
-0.34253811836242676,
0.46512430906... |
Detailed Instructions: Given a sentence in Arabic, generate a new Arabic sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.
Q: « إن » ما « تَسْتَخْدَمُ » فيه إدغام التاء الثانية في الأصل في الذال « من نطفة » بسكون الياء وضمها « لتتوكل » على الله.
A: | أنت يُمْكِنُ أَنْ تَكْسُرَ a قطّة لتَجِدُ نعيمًا. | 9 | NIv2 | task414_mickey_ar_sentence_perturbation_generation | zs_opt | [
-0.7023552656173706,
0.6800304055213928,
0.09157741069793701,
0.05115119367837906,
-0.4216518700122833,
-0.4771284759044647,
1.2313618659973145,
0.8164267539978027,
-0.26253053545951843,
0.17546826601028442,
-0.3954298794269562,
0.3933231234550476,
-0.7457643151283264,
-0.04707186669111252... |
Instructions: A text is given in Bengali. Translate it from the Bengali language to the Hindi language. The translation must not omit or add information to the original sentence.
Input: प्रधानमंत्री मोदी ने गृहमंत्री श्री अमित शाह को विशेष रूप से बधाई देते हुए कहा कि हमारे गृहमंत्री अमित शाह जी जम्मू-कश्मीर और लद्दाख के लोगों के बेहतर जीवन को सुनिश्चित करने के लिए निरंतर कार्य कर रहे हैं।
Output: | শ্রী মোদী বলেছেন, ‘আমাদের স্বরাষ্ট্র মন্ত্রী শ্রী অমিত শাহ্জী জম্মু, কাশ্মীর ও লাদাখের মানুষের জীবনযাপনের মানোন্নয়নের লক্ষ্যে নিরন্তর কাজ করে চলেছেন। | 3 | NIv2 | task1010_pib_translation_hindi_bengali | zs_opt | [
0.14301267266273499,
0.13979139924049377,
0.43956494331359863,
-0.5027718544006348,
0.05196986719965935,
-0.7842124700546265,
0.2022358775138855,
-0.28154921531677246,
-0.4095548987388611,
-0.0029265705961734056,
-0.6300578117370605,
-0.13000327348709106,
-0.1346571296453476,
0.21955651044... |
In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: insult and non-insult. Insult is any lanugage or act that is disrespectful or scornfully abusive.
Ex Input:
Comment: These people are idiots
Ex Output:
Insult
Ex Input:
Comment: Just so you know, if you're government issued ID say's you're female but you present as male you're not allowed to board a plane in Canada.
Ex Output:
Non-insult
Ex Input:
Comment: I thought Pride was supposed to be about inclusivity. No one should be surprised that gays can also be prejudiced.
Ex Output:
| Non-insult
| 1 | NIv2 | task328_jigsaw_classification_insult | fs_opt | [
-0.9082333445549011,
0.4920274019241333,
0.7560965418815613,
-0.4404401183128357,
-0.03391226381063461,
-0.3042948246002197,
0.6215736269950867,
0.9955030679702759,
0.6175345182418823,
0.610775351524353,
-0.4856443405151367,
-0.18341633677482605,
-0.1043245941400528,
-0.9405991435050964,
... |
Instructions: In this task, you are given a sentence or phrase in English. You must translate it to Xhosa in a way that is equivalent in terms of meaning and grammatically correct.
Input: The handling of any type of power boat is governed in general by the common sense rules of seamanship.
Output: | Ukuphatha naluphina uhlobo lesikhephe elinamandla ilawulwa ngokoburhulumente ngokwengcinga eziqhelekileyo kumthetho woomatiloshe benqanawa. | 3 | NIv2 | task872_opus_xhosanavy_translation_eng_xhosa | zs_opt | [
0.405838280916214,
0.32642775774002075,
-0.48172396421432495,
-1.0836420059204102,
-0.16713157296180725,
-1.1997672319412231,
0.9346300959587097,
0.2684977352619171,
0.25004053115844727,
-0.3125537633895874,
-0.017346475273370743,
-0.5588887929916382,
-0.06815445423126221,
-0.2786579728126... |
Definition: Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.
Input: jump and look around left thrice
Output: | I_JUMP I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK | 2 | NIv2 | task130_scan_structured_text_generation_command_action_long | zs_opt | [
0.09548939764499664,
0.4013271629810333,
-0.35974836349487305,
-0.007896104827523232,
0.25207066535949707,
-0.04911684989929199,
0.43267273902893066,
0.02269468642771244,
-0.04229002445936203,
-0.07858000695705414,
-0.7322475910186768,
-0.21488675475120544,
-0.8012762069702148,
-0.09813271... |
In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal.
Here are the defications of each category:
1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows
2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows
3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows
4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows
5. Comparative: Comparing two rows in the table, regarding their values in one column
6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows
7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows.
Here are the definitions of logical operators for understanding of command:
1. count: returns the number of rows in the view.
2. only: returns whether there is exactly one row in the view.
3. hop: returns the value under the header column of the row.
4. and: returns the boolean operation result of two arguments.
5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column.
6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column.
7. argmax/argmin: returns the row with the max/min value in header column.
8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column.
9. eq/not_eq: returns if the two arguments are equal.
10. round_eq: returns if the two arguments are roughly equal under certain tolerance.
11. greater/less: returns if the first argument is greater/less than the second argument.
12. diff: returns the difference between two arguments.
13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument.
14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument.
15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument.
16. filter_all: returns the view itself for the case of describing the whole table
17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument.
18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument.
19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument.
20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument.
21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument.
22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.
One example: round_eq { sum { all_rows ; casinos } ; 217 }
Solution is here: aggregation
Explanation: In this example sum returns the sum of the values in all of the casinos rows. Hence, aggregation is right category.
Now, solve this: eq { hop { nth_argmin { filter_eq { all_rows ; pba team ; formula shel } ; pick ; 2 } ; player } ; arnold rodriguez }
Solution: | ordinal | 6 | NIv2 | task212_logic2text_classification | fs_opt | [
0.21964630484580994,
-0.30885472893714905,
-0.36885225772857666,
0.2988694906234741,
0.41732579469680786,
-0.5481292009353638,
0.769274115562439,
0.693027675151825,
0.24964484572410583,
-0.025244956836104393,
-0.14885058999061584,
0.16923771798610687,
-0.004334928467869759,
0.4120887815952... |
Detailed Instructions: In this task, you're given the beginning and the ending of a three-part story. Your job is to complete the short story by writing a middle sentence that seamlessly connects the first and last sentence. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the middle sentence, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.
Q: Beginning: Joe was walking home one night. Ending: He went straight to the cafeteria and had a long dinner.
A: | Joe started to feel hungry. | 9 | NIv2 | task067_abductivenli_answer_generation | zs_opt | [
-0.7589688897132874,
0.8421772718429565,
-0.45369619131088257,
0.1531175673007965,
-0.6935992240905762,
0.09419582784175873,
0.996738612651825,
0.5920427441596985,
-0.4871579110622406,
0.05388423800468445,
-0.19209381937980652,
0.13374657928943634,
-0.2742849588394165,
-0.09392014145851135... |
In this task, you are given a sentence in the Spanish language. Your task is to translate the Spanish sentence into the English language.
Ex Input:
La medición más precisa de la temperatura corporal en un paciente inconsciente, debe obtenerse a nivel
Ex Output:
The most accurate measurement of body temperature in an unconscious patient should be obtained at
Ex Input:
El tratamiento antibiótico recomendado en una diarrea aguda por Clostridium difficile es
Ex Output:
The recommended antibiotic treatment for acute diarrhea caused by Clostridium difficile is
Ex Input:
Una de las características del Proceso de Enfermería es
Ex Output:
| One of the characteristics of the Nursing Process is
| 1 | NIv2 | task1433_head_qa_language_translation_es_to_en | fs_opt | [
0.07330727577209473,
-0.33546900749206543,
-1.3006086349487305,
-0.2712404429912567,
0.14134515821933746,
-0.8841440081596375,
-0.4182620048522949,
0.36198684573173523,
0.22040674090385437,
0.08059415966272354,
0.17635558545589447,
0.23536492884159088,
-0.005706921685487032,
0.187191367149... |
You are given a sentence in Persian. Your job is to translate the Farsi sentence into Spanish.
--------
Question: و آنچه مادر می خورد ، زیر بنای پیش بینی جنین است. و آنچه مادر می خورد ، زیر بنای پیش بینی جنین است.
Answer: Y la base de la predicción del feto es lo que come su madre.
Question: اما اتفاقی که می افته اینه که کریسپر توسط هزاران هزار محقق استفاده می شه تا کار های خیلی خیلی مهمی انجام بشه ، مثل ایجاد نمونه های بهتر از بیماری ها در حیوانات ، یا راهکار هایی برای تولید مواد شیمیایی ارزشمند و تولید صنعتی اونها در مخازن تخمیر ، و یا حتی تحقیقات بنیادی در مورد اینکه ژن ها واقعا چطور کار می کنند.
Answer: Pero está ocurriendo que miles y miles de científicos están usando CRISPR para hacer un trabajo muy importante, como mejores modelos de enfermedades en animales, por ejemplo, o para abrir caminos que produzcan productos químicos valiosos y colocarlos en cubas de fermentación y producción industrial, o incluso hacer investigación muy básica sobre lo que hacen los genes.
Question: این ها واقعی اند!
Answer: | ¡Eran reales!
| 7 | NIv2 | task1267_ted_translation_fa_es | fs_opt | [
-1.021592617034912,
0.44465190172195435,
-0.8176197409629822,
0.22027671337127686,
-0.9146369695663452,
0.2510935068130493,
-0.0584305040538311,
1.203826665878296,
0.4729224443435669,
-0.38603174686431885,
-0.7572882771492004,
0.21079643070697784,
-0.4071834981441498,
0.32164373993873596,
... |
Teacher: You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into English.
Teacher: Now, understand the problem? If you are still confused, see the following example:
Os astrónomos acreditam que cada estrela da galáxia tem um planeta, e especulam que até um quinto deles tem um planeta do tipo da Terra que poderá ter vida, mas ainda não vimos nenhum deles.
Solution: Astronomers now believe that every star in the galaxy has a planet, and they speculate that up to one fifth of them have an Earth-like planet that might be able to harbor life, but we haven't seen any of them.
Reason: The Portugese sentence is correctly translated into English, because the meaning is preserved.
Now, solve this instance: O que é que isso fez?
Student: | What did it do? | 2 | NIv2 | task1274_ted_translation_pt_en | fs_opt | [
-0.16633576154708862,
0.5033619403839111,
0.22515907883644104,
-0.5582754611968994,
0.006991141475737095,
-0.7993054986000061,
-0.4723395109176636,
0.5188425779342651,
0.5202935934066772,
-0.44947996735572815,
-0.16606709361076355,
0.29079633951187134,
-0.4092658758163452,
-0.5289518833160... |
Given a sentence in Spanish, generate a new Spanish sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.
Ser iped por un coche puede disminuir su valor. | Ser atropellado por un coche puede eliminar su seguridad. | 0 | NIv2 | task417_mickey_es_sentence_perturbation_generation | zs_opt | [
-0.5293688178062439,
0.43930739164352417,
0.4689473509788513,
-0.01458890549838543,
-0.2482803463935852,
-0.6367733478546143,
0.43680518865585327,
1.5722614526748657,
0.004408174194395542,
-0.7376372814178467,
-0.9711488485336304,
-0.06315552443265915,
-0.7984341382980347,
-0.1477952897548... |
Teacher: Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.
Teacher: Now, understand the problem? If you are still confused, see the following example:
I've read this book with much expectation, it was very boring all through out the book
Solution: Negative
Reason: Review writer does not like the book because it was boring, therefore it is a negative review.
Now, solve this instance: I Have had trouble with HP and XP since upgrading. Although they say it is xp compatable with driver, it is not. Will cause system to lock up and when I called HP they blamed XP. Bought a Epson and first time install without a hitch. Hope this helps and God bless you!
Student: | Negative | 2 | NIv2 | task493_review_polarity_classification | fs_opt | [
-0.36525818705558777,
-0.7189925909042358,
0.8311477899551392,
-0.47675907611846924,
0.6656415462493896,
-0.8372464179992676,
0.6282777786254883,
0.48718124628067017,
0.9813982248306274,
0.49599987268447876,
0.4572504758834839,
-0.5260633826255798,
-0.5461647510528564,
-0.556446373462677,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.