inputs stringlengths 39 523k | embedding listlengths 1.02k 1.02k |
|---|---|
Given the task definition and input, reply with output. You are given a sentence in Polish. Your job is to translate the Polish sentence into Galician.
Wasze szanse są więc bardzo niewielkie.
| [
-1.1687629222869873,
1.6616886854171753,
0.34955763816833496,
-0.7321102619171143,
-0.11226227879524231,
-0.8103301525115967,
0.7469739317893982,
-0.3246676027774811,
-0.2915881872177124,
-0.16240926086902618,
-0.395254909992218,
0.8211802840232849,
-0.1674988865852356,
0.32344236969947815... |
Detailed Instructions: In this task you will break down a question into the basic steps required to answer it.
A question decomposition is a numbered list of operations that must be performed to answer the original question. Imagine explaining your question to a friendly droid by listing each action it should take in order for the question to be answered. Each step in our decomposition should refer to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.)
Here are the list of step templates and their description:
Select: A select step is used to return a set of objects. There are no references to previous steps in a select step. template: Return [attributes]
Filter: A filter step is used to return results from a previous step to which a certain condition applies. template: Return [#step] [condition]
Project: A project step should return certain attributes of the results of a previous step. template: Return [attributes] of [#step]
Aggregate: An aggregate step returns an aggregator function applied on a step's result. template: Return the [aggregator] of [#step].
Group: A group step is an aggregator applied on attributes. template: Return the [aggregator] of [#step] for each [attribute]
Superlative: A superlative step is used to return the result with a highest/lowest attribute among other results. template: Return [#step1] [where] [#step2] [is] [highest / lowest]
Comparative: A comparative step is used when we need to compare an attribute with a number to filter results. template: Return [#step1] [where] [#step2] [comparator] [number]
Union: A union step is used to return results of two steps together. template: Return [#step1] [or / ,] [#step2]
Intersection: An intersection step returns the result that two steps have in common. template: Return [attribute] of both [#step1] and [#step2]
Discard: A discard step returns result of a step and excludes result of another step from it. template: Return [#step1] besides [#step2]
Sort: A sort returns result of another step in a specific order. template: Return [#step1] [ordered / sorted by] [#step2]
Is true: An is true step checks a condition on another result and returns a true or false. template: Return [is / if] [condition]
Arithmetic: An arithmatic step operates an arithmatic operation on one or more steps. template: Return the [arithmetic op.] of [#step1] [and] [#step2].
Q: question: If the lock in the image on the right is in the locked position.
A: | [
1.0313048362731934,
-0.32911089062690735,
-0.8456498384475708,
0.6302503347396851,
0.3889753222465515,
-0.3069089651107788,
1.2834460735321045,
0.4465152621269226,
-0.43224233388900757,
0.39127710461616516,
-0.5034804344177246,
-0.23416753113269806,
-0.02764139324426651,
0.7526142597198486... |
You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.
Example Input: password = 66uk84COmRoRx5!p5NRnhDiTtPE.c7CHu876bO23
Example Output: 20
Example Input: password = twIkOFN2UDgQoD
Example Output: 0
Example Input: password = f3LTqOPWn8ORH!Stn3bv0AUq.DGn
Example Output: | [
0.8080022931098938,
1.103971004486084,
-0.020266719162464142,
-0.7251259088516235,
-0.041617270559072495,
-0.5801440477371216,
1.378580093383789,
0.005890917032957077,
0.1836865246295929,
-0.8375217318534851,
0.0766400396823883,
-0.016401678323745728,
-0.8044615983963013,
-0.58318972587585... |
Detailed Instructions: Provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is -
'.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc.,
'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes,
'ADP': Adposition is a cover term for prepositions and postpositions,
'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner,
'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause,
'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context,
'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea,
'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction,
'PRT': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech,
'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context,
'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object,
'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause,
'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.
Q: Sentence: During Mr. McGovern 's nine-year term as president , the company 's sales rose to $ 5.7 billion *U* {{ from }} $ 2.8 billion *U* and net income increased to $ 274 million *U* from $ 130 million *U* , the statement said 0 *T*-1 .
Word: from
A: | [
0.24151970446109772,
0.15877249836921692,
-0.21591022610664368,
0.16356110572814941,
-0.10788139700889587,
-0.45844364166259766,
0.4546487331390381,
0.6307851076126099,
-0.11762816458940506,
-0.006695467047393322,
-0.6477198600769043,
0.20662251114845276,
-0.6454688310623169,
0.15379899740... |
Q: In this task, you are given a sentence in the Hindi language and your task is to convert it into the English language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).
एसोसिएटेड प्रेस से बात करते हुए, आर्मी ब्रिगेडियर जनरल सैमुअल सालिहु ने इनकार किया कि आगजनी के लिए नाइजीरियाई सैनिक जिम्मेदार थे।
A: | [
-0.1439065933227539,
0.7318019270896912,
0.9178392887115479,
-0.7097207307815552,
0.4306204915046692,
-0.974595844745636,
0.4846840500831604,
0.7992620468139648,
-0.22905036807060242,
-0.024524204432964325,
-0.0790824443101883,
-0.2676609456539154,
-1.0008251667022705,
-0.09542478621006012... |
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.
--------
Question: Category: PRESIDENTIAL FIRSTS
Clue: The first president to cross the Atlantic Ocean while in office, he did so to meet with other world leaders
Answer: wilson
Question: Category: HOLIDAYS & OBSERVANCES
Clue: As the Constitutional bicentennial reminded us, the Constitution was signed on this date in 1787
Answer: september 17th
Question: Category: FAMOUS WOMEN
Clue: This 1904 Radcliffe graduate was a suffragist, political activist, Vaudeville performer & writer
Answer: | [
-0.30913791060447693,
1.0074563026428223,
-0.10476367175579071,
0.11459797620773315,
-0.2981225848197937,
-0.4550957679748535,
0.8228176832199097,
-0.2702779173851013,
0.6624036431312561,
0.471463143825531,
0.31654447317123413,
-0.5115693807601929,
-0.37270858883857727,
0.10687603056430817... |
Definition: This task is about translating a given Yoruba language sentence to English.
Input: Àwọn ènìyan ilẹ̀ Adúláwọ̀, nítorí wọ́n máa fi ẹ̀mí ṣe é, mo rò bẹ́ẹ̀.
Output: | [
0.7201787829399109,
0.8810514211654663,
0.24489659070968628,
-0.6315107345581055,
-0.5060640573501587,
-0.502554178237915,
-0.0451069101691246,
0.7400259375572205,
0.21395127475261688,
-0.4590721130371094,
0.04996220022439957,
-0.40352553129196167,
-0.47335436940193176,
0.20140835642814636... |
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.
F: Jim, can you help me fill these forms? My assistant has been ill and went to see the doctor just now. ,M: Just tell me what needs to be done. I'm free till the 4:00 o'clock meeting begins.
(A) F: It's so nice of you. Form 1-4 need to be filled in. Take your time. (B) F: You are a life saver! My assistant is attending the meeting and is not available now. (C) F: It's so nice of you. My assistant will be on sick leave and is going to see the doctor tomorrow. (D) F: I’m sorry, I didn’t understand. Could you repeat a little louder, please?
A
M: Hi, Helen, I saw you yesterday with a lovely little girl at the market. Your daughter? ,F: No, she's my sister's daughter, she's just visiting and will be staying with us for a couple of days.
(A) M: Oh, that's your niece then, she's really cute. (B) M: Just a minute! I do not quite follow what you are saying, would you mind repeating that? (C) M: Your niece is so cute, I didn't know your brother had a daughter. (D) M: Your daughter looks a lot like you.
A
F: There is a sales event at the shopping center this weekend. Let's go and have a look. ,M: I don't want to go. ,F: What's wrong? Don't you always go check out these things? ,M: Yes, but I've spent all my pocket money this month.
(A) F: Do you not want to go check out these things because you are not interested? (B) F: So you're not going to class because you don't have any money? (C) F: I’m sorry, I don’t understand. Could you say it again? (D) F: I see. You don't have any money because you haven't had a part-time job recently.yaobu
| [
0.26344117522239685,
-0.0993211567401886,
-0.25175195932388306,
-0.3019029498100281,
0.5111653804779053,
-0.05113004893064499,
0.6902945637702942,
0.5636764764785767,
0.6216562390327454,
-0.21137410402297974,
-0.43046680092811584,
0.20944738388061523,
0.40535980463027954,
-0.19602651894092... |
You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Galician.
今は共通点を見つけることができます実際には会ったことはないけれどもインターネットや他の通信手段を通じては会っている人達と... 組織化することもできます － みんなが集まって何とかしなければならない問題や不正に対処したりして... 人類の歴史上ユニークな時代だと思いますでもそれは始まりに過ぎません本当のグローバル社会の創造の... | [
-0.07151840627193451,
0.579055905342102,
-0.09905889630317688,
-0.7041106820106506,
-0.42087721824645996,
-0.8479893803596497,
0.09850865602493286,
0.10338463634252548,
-0.5308571457862854,
-0.03354649990797043,
-0.1142508015036583,
0.2907092273235321,
-0.40539154410362244,
0.3627247810363... |
Teacher: The provided file includes inquiries about restaurants, and we ask you to translate those to the Japanese language. Please bear in mind the following guidlines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for special placeholders. Please do the same in your translations.
Teacher: Now, understand the problem? If you are still confused, see the following example:
are there any " italian " restaurants nearby with 4 star reviews ?
Solution: 近くに4つ星評価の" italian "レストランはある？
Reason: The translation correctly preserves " italian " entity and is accurate
Now, solve this instance: tell me the " american " restaurants .
Student: | [
-0.569130539894104,
0.2296835035085678,
0.09337511658668518,
0.06285607814788818,
0.2403467893600464,
-0.5731017589569092,
0.5717145204544067,
0.6063652038574219,
-0.25984933972358704,
-0.6015483140945435,
0.4984228014945984,
-0.16702497005462646,
-0.04490743577480316,
0.02384517341852188,... |
Detailed Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to write a single word that describes the genre that the two sentences belong to, such as face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction.
Q: Sentence 1: Households may choose to save less of their disposable income and maintain their current level of consumption especially if they consider the higher tax payments to be temporary. Sentence 2: Households cannot decide to save less of their income and keep consumption up if the tax payments aren't permanent.
A: | [
-1.2246639728546143,
0.5361735820770264,
0.00561075285077095,
-0.07691238075494766,
0.07142610102891922,
-0.3118283748626709,
0.3088880479335785,
1.1642515659332275,
-0.09972389042377472,
-0.04302679002285004,
-0.20299193263053894,
0.05452222377061844,
-0.7249705791473389,
-0.6378917694091... |
Detailed Instructions: You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Spanish.
Q: ニューヨークにいるかもしれない
A: | [
0.08008233457803726,
0.4713234305381775,
-0.13248425722122192,
-0.3172473609447479,
0.3094971179962158,
-0.725502610206604,
-0.966301441192627,
1.0766154527664185,
0.9384677410125732,
-0.38205674290657043,
0.6612792611122131,
0.4801994562149048,
-0.7645752429962158,
0.02885795570909977,
... |
You will be given a definition of a task first, then some input of the task.
Given a question and its paraphrases, answer the question. The answer should exactly answer all the questions given without any ambiguity. Don't give partial answers.
Questions: ['when is the feast day of saint elizabeth?']
Output: | [
-0.17717991769313812,
0.890871524810791,
-0.23358480632305145,
-0.24802926182746887,
-0.6202666163444519,
-0.559931218624115,
0.8170756101608276,
-0.19250336289405823,
0.12138976156711578,
-0.030842166393995285,
0.027095794677734375,
-0.16431044042110443,
-0.000749026658013463,
0.217940896... |
Detailed Instructions: Classify the given tweet into the three categories: (1) 'Hate Speech', (2) 'Offensive' and (3) 'Neither'. 'Hate Speech' is kind of a threating statement or sometimes include call for violence while 'offensive' statement just offensds someone. 'Neither' is when it doesn't fall into Hate Speech or Offensive category.
Q: RT @Meet_Nallah: “@mckenxcassie: Some of y'all hoes so worried about y'all eyebrows y'all forgot y'all had a mustache 😂😭😭” LMAO
A: | [
-0.05554526299238205,
0.12599919736385345,
0.6341875791549683,
0.27730995416641235,
-0.04799122363328934,
-0.7768539190292358,
0.11977563798427582,
0.8025326132774353,
0.4742022156715393,
0.6001786589622498,
-0.5029667615890503,
-0.6096885204315186,
-0.3339610993862152,
-0.9834691286087036... |
instruction:
Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.
question:
Because I remember loving and being absolutely terrified at these books when I was a kid, I recently purchased all 3 and just received them today. To my horror (and not in a good way) I found that they've published them with a DIFFERENT ILLUSTRATOR! With all due respect to Mr. Helmquist (the new guy) and certainly to Mr. Schwartz (the original author), these books were made for me by the art of Stephen Gammell. I'm sure they did this because so many parents tried to get the books banned in their day because of the ghastly drawings, but this is really a tragedy. I would suggest looking elsewhere for original copies of the books as they should be seen. Don't buy them here - you'll be missing out on part of what made these books so wonderful in the first place.
answer:
Negative
question:
This book is not for everyone. It is extremely scary and disturbing. At the same time, it is a fascinating look at the police work and prosecution that brought the murderous Manson Family to justice. The book is hard to put down; the in depth discussion on presenting a criminal case in court and developing evidence to support the case is outstanding. The main complaint is that the book is a few hundred pages too long. The author seems a little too self-promoting, but then again he did get a prosecution on one of the biggest murders in history.
answer:
Positive
question:
i bought this for my wife to replace her rabbit habbit that broke after a few uses. let me first say that it say 1 1/2 inches no it makes the rabit habit look tiny. its hugeat least 1 3/4 inch around. but its much slower than the other dosent vibrate near as fast. other than the size being more real size she liked the rabit habit better but we just got this one maybe it will get better. just goes to show bigger isnt better always. needs more power
answer:
| [
0.4412446618080139,
-0.3333909809589386,
0.07769277691841125,
-0.28059202432632446,
0.9074718356132507,
-0.16597279906272888,
1.1669490337371826,
0.6685419082641602,
0.02336950972676277,
0.12744833528995514,
-0.7462257146835327,
0.41030216217041016,
-1.0998363494873047,
-0.3194857239723205... |
Q: In this task, you're given a statement, the genre to which that statement belongs, and a label indicating if the statement should be agreed with (entailment), disagreed with (contradiction), or neither (neutral). Your job is to write a sentence that describes the genre that follows the tone with respect to the statement, as indicated by the label. If sentence X agrees with sentence Y, the can be concluded from one another. If sentence X disagrees with sentence Y, they can not be correct at the same time. The sentence must also belong to the genre specified.
Statement: RESPA generally prohibits compensated referrals in connection with real estate settlements involving federally related mortgage loans.
Label: contradiction.
Genre: government.
A: | [
-1.4110467433929443,
0.8045536279678345,
0.7483149766921997,
-0.3338860869407654,
0.10478433221578598,
0.031255774199962616,
0.3353496193885803,
0.6676064729690552,
0.4904007613658905,
-0.08290659636259079,
-0.2539733648300171,
0.31140410900115967,
-0.8098753690719604,
0.22488370537757874,... |
Given the task definition, example input & output, solve the new input case.
In this task, you are given a text which is the body of a document. You are given a question and options. Pick the correct number. Don't generate anything else apart from the numbers provided in options.
Example: Text: The Mansfield Building Society is a UK building society which has its headquarters in Mansfield Nottinghamshire. It is a member of the Building Societies Association.
Question: The document can be classified to which topic? Options: 1)Animal, 2)Plant, 3)Building, 4)Company, 5)WrittenWork
Output: 3
Mansfield Building Society is a UK building society. Hence, option 3 is the correct answer
New input case for you: Context: Kate Havnevik is a Norwegian singer and songwriter. Her debut album the critically acclaimed electronica-infused Melankton was released in March 2006 on iTunes and April 2006 (on physical CD) in Norway only before being licensed internationally to Universal Republic USA later. Havnevik had a string of song placements in big US TV-series such as Grey's Anatomy West WIng OC InJustice Windfall etc...
Question: The document can be classified to which topic?
Options: 1)Building, 2)MeanOfTransportation, 3)Artist, 4)WrittenWork
Output: | [
0.11188413202762604,
0.5353521704673767,
-0.005963227711617947,
0.3705082833766937,
0.6127137541770935,
-0.022908654063940048,
-0.09091086685657501,
0.6524167060852051,
-0.5816076993942261,
0.1661292314529419,
-0.3743336796760559,
-0.5647430419921875,
-0.04431983828544617,
-0.6871646642684... |
Definition: Given an Amazon review, indicate whether it is a 'Positive Review' or 'Negative Review'.
Input: Meet expectations
Output: | [
-0.2818005681037903,
-0.7831701040267944,
-0.0024568275548517704,
-0.061942584812641144,
0.058305349200963974,
-0.5909996628761292,
0.4996422529220581,
-0.21645855903625488,
0.5336356163024902,
0.8763557076454163,
-0.36515650153160095,
-0.23405833542346954,
-0.3189842700958252,
0.147077813... |
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 document towards the entity Nikki Haley ? The unprecedented presentation - which Haley said involved intelligence that had to be declassified - is part of President Donald Trump’s new Iran policy which promises a harder line toward Tehran. That would appear to include a new diplomatic initiative.
Positive
What is the sentiment of the following document towards the entity Aranibar ? The practice of clay eating is now a part of the region's tradition says Aranibar .
Positive
What is the sentiment of the following document towards the entity Jared Kushner ? âGeneral Kelly respects Jared a lot and General Kelly will make that call â Trump said at a joint news conference with Australian Prime Minister Malcolm Turnbull at the time.
| [
-0.3947885036468506,
0.18631607294082642,
-0.15770748257637024,
0.37082451581954956,
-0.4959317445755005,
-0.5150590538978577,
1.0823307037353516,
0.6814002990722656,
0.2406477928161621,
0.11547033488750458,
-0.33491307497024536,
0.42348814010620117,
-0.5402135848999023,
0.1817162036895752... |
In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: threat and non-threat. Threat is a statement that someone will be hurt or harmed, especially if the person does not do something in particular.
Comment: His morbid obesity will come back to haunt him and kill him. | [
-0.7732038497924805,
0.9147821664810181,
0.9257622957229614,
-0.11561974883079529,
-0.15706941485404968,
-0.23004019260406494,
1.1932052373886108,
0.6466941237449646,
-0.04928245767951012,
0.0976436585187912,
-0.3943081498146057,
0.042701102793216705,
-0.9140729904174805,
-0.42986503243446... |
Instructions: In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with "TIFU by", followed by a situation that caused humor. The title should contain 7-12 words, ideally.
Input: Text: this happened about a month ago. i work for the records office in an inactive prison. we are pretty much a warehouse for paroled prisoner files. facilities order files when the assholes violate parole and are brought back, and we send them out. there are only six people that work in my particular area, so we all have quite a bit of freedom. this place is huge, and we have files stored all over the building, a lot of them in creepy, run down spots. so, there are a lot of good spots to scare someone. we make a game of it some days. every morning, we get prisoners from the surrounding facilities to come in and clean the offices. a guy in my office is responsible for taking the files that we are shipping down to the mailroom and bringing the prisoners back up. on this particular morning, he used a dolly and had to take the elevator down. no one uses the elevator but us, so i decided to wait around the corner for a good scare when he came back up. a few minutes go by, i hear the elevator kick on... the doors open... the dolly rolling... wait... wait... i jump out, yell at the top of my lungs and am immediately thrown and pinned against the wall. holy shit, it was one of our prisoners. as i was sure i triggered some kind of involuntary response in him, i frantically tried to apologize and explain myself, literally fearing for my life. once he realized what had happened, he let me go, apologized for the physical contact, and walked off. fearing the loss of my job, i never said a thing to anyone about it. i'm just glad i walked away un-shanked.
Output: | [
0.15293428301811218,
0.634543776512146,
-0.379321813583374,
-0.057529233396053314,
0.44014424085617065,
-0.1548938751220703,
0.02134549617767334,
0.6035556793212891,
0.4045241177082062,
0.34629493951797485,
-0.18826192617416382,
-0.06970900297164917,
-0.6735702753067017,
0.0039844755083322... |
You will be given a definition of a task first, then some input of the task.
Given news headlines, an edited word and funniness labels. The original sentence has word with the given format {word}. Create new headlines by replacing {word} in the original sentence with edit word. Your task is to generate answer "Yes" if an edited sentence matches funniness label, otherwise generate answer "No".
News Headline: {Paul Manafort} Flew 18 Times To Moscow And Frequently Reached Putin ’s Allies , Records Show
Edit: Eagle
Label: Not Funny
Output: | [
-0.6587334871292114,
0.1634232997894287,
0.16372855007648468,
-0.2736685574054718,
-0.4450669586658478,
-0.5732800364494324,
0.29641759395599365,
0.8031163215637207,
0.08443258702754974,
-0.19908781349658966,
-0.9249199628829956,
-0.29887884855270386,
-0.4496927261352539,
-0.02021148242056... |
Detailed Instructions: In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about "doctors", you can talk about "health" or "diagnosis", but don't mention "aliens". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: "She likes cakes." is changed to "She doesn't like cakes."
Problem:Beginning: Jane was making strawberry cake. Middle: Jane didn't have enough strawberries to cover the whole cake. Ending: Her cake still tasted delicious.
Solution: | [
0.31174880266189575,
0.6837534308433533,
-0.025340154767036438,
-0.278110146522522,
-0.3523658514022827,
-0.07445226609706879,
0.362968772649765,
0.8343499302864075,
-0.893017590045929,
-0.2412814497947693,
-0.40238940715789795,
0.4144023358821869,
-0.418657511472702,
0.0012229221174493432... |
Definition: In this task you will be given a list of numbers. A list is shown by two brackets and comma-separated numbers inside, like: [1,2,3]. You should remove all of the even numbers from the list. If every number in the input list is even an empty list should be returned. Zero should be counted as an even number.
Input: [7, 143, 39, 35, 90, 143]
Output: | [
-0.2885812520980835,
0.5590546131134033,
-0.5060336589813232,
-0.5807271599769592,
0.2963465750217438,
0.011480672284960747,
0.6796685457229614,
0.36995840072631836,
0.05832390487194061,
0.38880765438079834,
-0.7882400751113892,
0.2490656077861786,
-0.2153070569038391,
-0.12716490030288696... |
In this task, you are given an utterance, which is a part of a conversation between a user and an agent. Your job is to detect the speaker. The user usually commands the agent to schedule events, retrieve event information, and check the schedule. While the agent's response is an answer to the user's questions or follow-up questions on the user's command. Answer with "User" or "Agent".
Q: cancel my 3 o clock meeting with judy's manager
A: | [
-0.9139401912689209,
0.698884904384613,
-0.48630285263061523,
-0.43038684129714966,
-0.29705220460891724,
0.034508246928453445,
0.4040445387363434,
-0.23458561301231384,
0.7396513223648071,
-0.13268056511878967,
-0.2770308256149292,
-0.10875022411346436,
-0.7799372673034668,
0.393800973892... |
In this task, you have to generate the title of the recipe given its required ingredients and directions.
Q: ingredients: '2 cups chocolate ice cream', '1/3 cup milk', '1/4 cup malted milk powder', '3 tablespoons chocolate syrup', 'chocolate covered malt balls',<sep> directions: 'In a blender, combine 2 cups chocolate ice cream, 1/3 cup milk, 1/4 cup malted milk powder, and 3 tablespoons chocolate syrup. Whirl until smooth and pour into a chilled tall glass (at least 16 oz.) or two chilled glasses (8 oz. each). Garnish with halved chocolate covered malt balls.'
A: | [
0.9623528122901917,
1.4464364051818848,
0.09912620484828949,
0.32160717248916626,
0.6884281039237976,
0.06495213508605957,
-0.3622438907623291,
-0.03384063392877579,
-0.2227938175201416,
-0.09473715722560883,
0.36844903230667114,
-0.08004257082939148,
-0.4254723787307739,
-0.20530359447002... |
In this task, you will be shown an extract from a movie plot. You need to read the extract and create questions that can be answered from the extract. Once you create a question you also need to provide the correct answer for it. Write your answer like "Question: your question, Answer: your answer". The questions should be well-formed and grammatically correct. The questions should be completely answerable from the given passage and should not require any external knowledge. Subjective questions are not allowed. Short answers containing words that are present in the passage are preferred. Create questions that result in factoid answers. A simple rule of thumb to decide whether a question is a factoid or not is to see if two different people with average reading/comprehension skills would come up with the same answer after reading the passage.
One example is below.
Q: Twenty-year-old Will Hunting of South Boston is a self-taught, genius-level intellect, though he works as a janitor at the Massachusetts Institute of Technology and spends his free time drinking with his friends, Chuckie (Ben Affleck), Billy (Cole Hauser) and Morgan (Casey Affleck). When Professor Gerald Lambeau (Stellan Skarsgård) posts a difficult mathematics problem as a challenge for his graduate students, Will solves the problem anonymously, stunning both the graduate students and Lambeau himself. As a challenge to the unknown genius, Lambeau posts an even more difficult problem. Lambeau chances upon Will solving the problem but Will flees the scene. That night at a bar, Will meets Skylar (Minnie Driver), a British student about to graduate from Harvard, who plans on attending medical school at Stanford and gives Will her phone number before leaving.
A: Question: How old is Will Hunting in the movie ?, Answer: Twenty years
Rationale: This is a good question which results in a factoid answer, and the answer is correct too.
Q: This article's plot summary may be too long or excessively detailed. Please help improve it by removing unnecessary details and making it more concise. (December 2015) (Learn how and when to remove this template message)The film begins with four teenagers at their senior prom: Jenny, Heather, Barry, and Sean. Heather begins to look for Barry, her boyfriend, who is making out with another girl in the darkness. Heather discovers them and attempts to drive away in Barry's car, alongside Jenny and Sean, who are in the backseat. Barry eventually gains access into the car, where Heather scolds him angrily. Heather does not pay attention to the road and ends up wrecking with another driver, who passes out in the ensuing confusion.The four teens decide that Sean should look after the unconscious driver, while Jenny, Heather, and Barry go look for help. While Sean looks after the driver, Heather, Barry and Jenny discover a rural real estate office occupied by Darla, a trashy insurance agent, who calls up her tow trucker boyfriend, Vilmer, to help out at the scene of the wreck. Meanwhile, Heather and Barry leave with Jenny, who loses them.Vilmer, a backwoods man with a robot leg, eventually arrives at the scene of the crash, where he snaps the unconscious driver's neck and chases Sean in his pickup, eventually running him over. Meanwhile, Heather and Barry come across a dilapidated farmhouse, where Barry looks for a way inside to use the bathroom while Heather waits on the porch. Barry is discovered by Walter, Vilmer's brother. While Heather waits on the porch, Leatherface appears, playing with her hair and then chasing her. After Leatherface catches her, he stuffs her inside a meat locker. While Barry is using the restroom, he discovers human remains in the bathroom, and Leatherface bludgeons him to death with a sledge hammer. After killing Barry, Leatherface removes Heather from the meat locker, hanging her on a meathook in midair.Jenny arrives back at the wreckage, only to find her boyfriend and the driver absent. She meets Vilmer, who shows her the bodies of Sean and the Driver. Vilmer then chases her in his truck, only for her to escape into the woods. After hiding in thicket, Jenny is attacked by Leatherface, wielding a chainsaw; he chases her through the woods, and back to the Sawyer house, where Jenny locks the door, but Leatherface begins to break it down by sawing through the wood panels. Jenny then discovers the remains of a Texas Ranger after taking refuge upstairs. She takes the Ranger's gun, attempts to shoot at Leatherface, but discovers that it has no bullets. Leatherface chases Jenny back upstairs, where she jumps out a window, and onto the roof. Jenny tries to use a telephone cable to escape, but Leatherface cuts the cable and Jenny crashes through the roof of the Sawyers' greenhouse. Jenny retreats back into the forest and arrives back at Darla's office, begging for help.Walter shows up and it turns out that Darla and Walter are in cahoots. Walter beats Jenny with an electric cattle prod, stuffs her in a gunny sack and then into Darla's trunk. W.E. leaves Darla to go pick up some pizzas she ordered earlier with Jenny in the trunk of her car. After getting the pizzas, she returns home with Jenny.The family terrorizes Jenny, who escapes into Darla's car, but is subdued by Vilmer, who jumps on the hood of the car. Jenny wrecks and is dragged back inside the house where she is treated by Darla, who gets her ready for dinner time. Jenny falls unconscious, but awakens in the early morning hours at a dinner table, clean and redressed in a skimpy pageant gown, with a cross dressed Leatherface, the family's apparent Grandpa (possibly an elderly Drayton Sawyer), and a family of stuffed corpses. Jenny screams in terror and soon the family is joined by a mysterious Rothman, who tells the family that they aren't doing their "jobs" correctly. Rothman makes an idle threat to Vilmer, and then takes his leave. After Vilmer crushes Heather's skull in anger, Jenny tries to escape, but is held down by Vilmer as Leatherface revves his chainsaw, preparing to behead Jenny.As Vilmer holds Jenny down, and Leatherface makes pathetic attempts to decapitate her, she manages to snatch Vilmer's remote to his cybernetic leg and uses it to dislocate his knee as an advantage to escape, which she succeeds in doing. Jenny escapes to the main road, with Leatherface in hot pursuit, where she is helped by an elderly couple, but the couple's RV is soon turned over by Vilmer and Leatherface. Jenny climbs out of the wreckage, barely harmed, and Leatherface and Vilmer pursue her on foot. An apparent "Order of the Illuminati" airplane operated by one of Rothman's colleagues, swoops over head and the blade grazes Vilmer's skull, ultimately killing him. Jenny watches as Vilmer finally dies while Leatherface screams in horror and frustration, grieving the loss of his elder brother.A black limousine appears, and Jenny enters it only to discover Rothman inside. Rothman tells Jenny that her experience was supposed to be spiritual, but that it went awry and that Vilmer had to be stopped. She is dropped off at a hospital, where she sees a mysterious blonde woman being wheeled down a corridor as police question her.Meanwhile, Leatherface swings his chainsaw in frustration, where the screen cuts to black and the credits roll on.
A: | [
0.4433470666408539,
0.1293875277042389,
-0.11318742483854294,
-0.42134249210357666,
0.05792718753218651,
-0.3532363772392273,
0.5737251043319702,
0.7036536335945129,
-0.01103130728006363,
-0.3319568634033203,
-0.33887749910354614,
0.10389082133769989,
0.0865054577589035,
0.5948407649993896... |
In this task you will be given a list of numbers and you need to subtract every value in the list with the index it is at. The index of an elements shows its numerical order in the list(for example, in the list [7,10,4,5], the index of 7 is 1 and the index of 4 is 3) You should start the index at 1, so the first element in the list will be subtracted by one. For every element in the list you need to find "element - index" where the index of the beginning element is 1 and increments by 1 for each element. Put your result list in brackets.
Example input: [9,-6,-10,4,-8]
Example output: [8,-8,-13,0,-13]
Example explanation: Every element in the output list is equal to the element in the input list subtracted by its index. 9 - 1 = 8, -6 - 2 = -8, -10 - 3 = -13, 4-4 = 0, -8 -5 = -13. This is a good example.
Q: [-17, -13, 2, -14, 0, -16, -1, 10, 19]
A: | [
0.6713993549346924,
0.06589539349079132,
-0.9024749994277954,
-0.36758607625961304,
0.09647922962903976,
-0.5082558393478394,
0.9645702838897705,
0.6372997760772705,
-0.2459845095872879,
0.01845957711338997,
-0.596393346786499,
-0.12329760193824768,
-0.2878771424293518,
-0.0301684588193893... |
You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into English.
Ex Input:
מ "" ג: הו, עשרות פעמים.
Ex Output:
MN: Oh, tens of times.
Ex Input:
הראיתי לכם מודל אחר, את האחד — זוהי הדרך שארגנתי לעצמי כדי לצייר את השרטוט — אז הבנתי את הבעיה.
Ex Output:
I showed you the other model, the one — this is the way I organized myself so I could make the drawing — so I understood the problem.
Ex Input:
אז כשמדובר על המוח האנושי — יונאס פריזן, קולגה שלי ממכון קרולינסקה, מעריך שאנו מייצרים 700 תאי עצב חדשים ביום בהיפוקמפוס.
Ex Output:
| [
-0.8297673463821411,
0.056494273245334625,
-0.031782329082489014,
0.1334008276462555,
-0.011942100711166859,
-1.0258376598358154,
-0.1294800192117691,
-0.07378868758678436,
0.41700875759124756,
-0.16645590960979462,
-0.5305629968643188,
0.5647803544998169,
0.35396596789360046,
0.5273098945... |
Detailed Instructions: In this task, you are given books product reviews in German language. The goal is to classify the review as "POS" if the overall sentiment of the review is positive or as "NEG" if the overall sentiment of the review is negative.
Q: Ein packendes Zeitzeugnis . Diese Lebensgeschichte einer in jeder Hinsicht ungewöhnlichen Frau ist eine Gratwanderung zwischen Konvention und Leidenschaft, Liebe und Gleichgültigkeit, Juden- und Christentum, Burgeoisie und die Welt der Bohemien, Frieden und Krieg, Ost und West, Exil und Heimkehr. Angelika Schrobsdorff verleiht der Vita ihrer Mutter mit ihrem wunderbaren Schreibstil viel Würde, gewürzt mit der ihr eigenen Ironie, aber nie abflachend durch Verurteilung. Dieses Buch verdient allerhöchsten Respekt, allein das Zusammentragen und das durch das Schreiben erneute Eintauchen in das Geschehene zeugen von einer äusserst mutigen Autoren-Persönlichkeit. Ein Zeitzeugnis, das berührt und streckenweise erschüttert.
A: | [
-0.7431150078773499,
0.42305833101272583,
0.09411658346652985,
-0.2928040027618408,
-0.1860525757074356,
-0.04038441926240921,
1.0235204696655273,
0.30809396505355835,
1.1020729541778564,
0.5141304135322571,
-0.3314417004585266,
0.08783707022666931,
-0.1333540380001068,
-0.2327213138341903... |
Detailed Instructions: 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: The difference between simple interest and compound interest on Rs.1200 for one year at 10% per annum reckoned half yearly is
Option A: Rs.2.50
Option B: Rs.3
Option C: Rs.4
Option D: Rs.3.75
Option E: None
A: | [
0.33304107189178467,
0.31127598881721497,
-0.6489382386207581,
-0.36017459630966187,
-0.38620302081108093,
-0.4727778732776642,
1.3054049015045166,
0.8065270185470581,
-0.22578924894332886,
-0.05537538602948189,
-0.8937480449676514,
-0.20209747552871704,
-0.29625755548477173,
-0.2727143764... |
The task is to generate the correct answer for a given math problem.
Problem: mixture contains alcohol and water in the ratio 4 : 3 . if 5 liters of water is added to the mixture , the ratio becomes 4 : 5 . find the quantity of alcohol in the given mixture .
10
Problem: how many prime numbers are between 51 / 13 and 89 / 9 ?
2
Problem: a person borrows 20000 for 6 years at 8 % p . a . simple interest . he immediately lends it to another person at 9 % p . a . for 6 years . find his gain in the transaction per year .
| [
0.7948411703109741,
1.4898520708084106,
-0.1810367852449417,
-0.6641515493392944,
-0.601035475730896,
0.08942902088165283,
0.9260832667350769,
0.629612922668457,
0.396117627620697,
-0.12123969942331314,
-0.3157472014427185,
-0.08629044890403748,
-1.3043467998504639,
0.08261369168758392,
... |
Given the prompt and a response, classify the them to "yes" if response is "yes, and" type. Otherwise classify it as "no". "Yes, and" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated ("Yes") and then expand on that line of thought or context ("and..."). 1 In short, a "Yes, and" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a "Yes, and" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'.
Prompt: Look, I'm pretty sure these guys are robots.
Response: Yeah, but they are pretty nice. I mean, they gave me this horse, he brought me this bucket.
yes
Prompt: What can we do differently tonight's show?
Response: Oh, that's what was burnt on the poem! Those were the missing words.
no
Prompt: Welcome to our racially integrated Chinese restaurant. Would you like a hamburger chop suey?
Response: Yes sir, Mr. Mayor. Pants back on.
| [
0.3051909804344177,
0.5415644645690918,
0.46812593936920166,
0.5967143774032593,
0.024851977825164795,
-0.9749343395233154,
0.17030984163284302,
0.860180139541626,
-0.07030674815177917,
-0.36548593640327454,
-0.619675874710083,
0.23280031979084015,
-0.3968522548675537,
0.09525178372859955,... |
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: Landing ships and craft.
Output: | [
0.29231658577919006,
0.7454732656478882,
-0.23551687598228455,
-0.3168513774871826,
-0.07321761548519135,
-0.7931103706359863,
0.8489303588867188,
0.47978493571281433,
-0.05284959450364113,
-0.10478554666042328,
-0.07412175834178925,
-0.22752121090888977,
-0.31116971373558044,
-0.414653688... |
Teacher:In this task, you have to generate the named entities (NER) given its ingredients of the recipe. Named entities are the names of the items without their quantity.
Teacher: Now, understand the problem? Solve this instance: 2 gal. green tomatoes, quartered, 8 pods hot pepper, 1 gal. onions (before cut), diced, 1/2 gal. bell peppers (before cut), diced, 2 Tbsp. black pepper, 2 Tbsp. salt, 3 pt. white vinegar, 5 c. sugar
Student: | [
-0.49080315232276917,
0.2754150629043579,
0.2153392732143402,
0.35912424325942993,
-0.3301175534725189,
-0.5507885217666626,
0.8781126737594604,
0.42081332206726074,
-0.48448359966278076,
-0.4352923333644867,
0.15179964900016785,
-0.006129945628345013,
-0.6270084381103516,
-0.2423339188098... |
Detailed Instructions: 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'.
Problem:21 July 2015 occured before 22 August 1987 but after 10 July 2006
Solution: | [
-0.08029216527938843,
0.2600194215774536,
-0.5138192772865295,
0.6976441144943237,
-0.4390884041786194,
-0.7943716049194336,
-0.026627864688634872,
1.0898959636688232,
-0.8641583919525146,
-0.1069585531949997,
-0.36866495013237,
-0.47971439361572266,
0.03188406676054001,
-0.152213364839553... |
Detailed Instructions: In this task you are given a passage in Bulgarian as the input content. You are expected to generate a suitable title for the passage which accurately summarizes the contents of the passage. The input is provided in the form of a long passage comprising of multiple sentences. The output should be restricted to a maximum of 20 words which describe the passage and its contents. The output can include words from the passage.
See one example below:
Problem: Content:Пръстена активизира енергийната програма и биополето на човека и много зависи на коя ръка и кой пръст носите вашият пръстен. Реклама Дясната ръка се счита за проводник на мъжката енергия и ако носите пръстен на дясната си ръка ще активизирате определени сфери от вашият живот. Пръстена носен на лявата ръка ще е проводник на женската енергия и ще има възможност да ви защити в определени ситуации. Трябва да се вземе под внимание и от какъв материал е изработен пръстена. Златото като активен слънчев метал активизира енергията, а среброто защитава притежателя си от негативно въздействие. Златен пръстен сложен на палеца на дясната ви ръка ще подобри вашето материално положение, ако сложите сребърен пръстен ще засилите вашата интуиция. Ако носите пръстен на палеца на лявата си ръка ще имате възможност да получите реални плодове от вашите знания е възможности. Показалецът съединява човека с Бога. Добре би било на този пръст да носите сребърно украшение. Средният пръст на дясната ръка отговаря за съдбата и кармата. Носенето на пръстен на средният пръст ще спомогне по‐ бързо човек да разчисти своите кармични дългове. Безименият пръст носи успех, хармония и любов в семейството. На безименият пръст на дясната ръка е добре да се носи златен пръстен, по този начин ще се активизират всички сфери във вашият живот. Също така този пръстен ще обединява енергиите на партньорите и ще активизира техните отношения. Венчален пръстен изработен от сребро може да доведе до това, че човека да стане хладен в отношенията си и да се стреми да не дава своята любов а само да приема чуждата. Ако съпрузите са се разделили то е желателно те да си върнат брачните пръстени и по този начин да дадат свобода на себе си и партньора си за нови отношения. Друг начин е да сложат брачният си пръстен на лявата ръка и по този начин да пречистят енергиите от миналият си брак. Ако желаете да станете общителни, то си сложете златен пръстен с червен камък на малкият пръст на дясната си ръка. Сребърен пръстен сложен на малкият пръст на дясната ръка ще донесе на притежателя си спокойствие в живота. Източник: actualno.com
Solution: Как правилно да носите пръстен и какво означава на различните пръсти
Explanation: This is an accurate title for the passage. It contains words from the passage and also other relevant points which succinctly summarize the contents.
Problem: Content:1 100 души с влезли в сила присъди се укриват от властите у нас. Това съобщи пред БНР Ивайло Димитров, началник на сектор „Издирване“ в Националната полиция. Около 20 от престъпниците са осъдени за убийство. Имало е и случаи, при които издирвани са опитвали да променят външността си. Имали сме и такива случаи. Няма да назовавам имена. Аз лично от практиката си се сещам за два такива случая, при които има интервенции върху лицето на издирвания, поясни още Димитров. България
Solution: | [
0.7500826120376587,
0.8139344453811646,
-0.9140198826789856,
-0.48851147294044495,
0.01602817326784134,
-0.6223347187042236,
1.1753463745117188,
1.2353949546813965,
0.29784220457077026,
0.11876507103443146,
-0.7395259737968445,
1.5764696598052979,
-0.1524275839328766,
-0.15997780859470367,... |
Given a sentence in English language, translate the sentence to Tagalog language keeping the meaning of the original sentence intact.
English sentence: The New Facebook Profile prevents me from keeping the recipe on my FB page. | [
0.12408290058374405,
-0.1006573736667633,
-0.4262922406196594,
-0.6724136471748352,
0.11943228542804718,
-0.9502432942390442,
0.6980212330818176,
0.6761028170585632,
0.0982389971613884,
0.05467701703310013,
0.601177990436554,
0.2809555232524872,
-0.5097891092300415,
-0.08992020040750504,
... |
In this task, you are given a sentence in English language and its corresponding French translation. Here, your job is to output "yes" if the translation is correct, otherwise output "no".
English: What's in it for me?
French: Quels en sont les avantages pour moi? | [
-0.17530079185962677,
0.7037903666496277,
0.5750202536582947,
0.013448473066091537,
0.20805999636650085,
-0.560242235660553,
0.32307755947113037,
0.4885452091693878,
0.8303879499435425,
0.37599247694015503,
-0.5040093660354614,
-0.149344801902771,
-0.865440845489502,
-0.6429958343505859,
... |
Teacher:In this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e. tagset of this corpus is 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, 'ADP': Adposition is a cover term for prepositions and postpositions, 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, 'AUX': An auxiliary is a function word that accompanies the lexical verb of a verb phrase and expresses grammatical distinctions not carried by the lexical verb, such as person, number, tense, mood, aspect, voice or evidentiality, 'CCONJ': A coordinating conjunction is a word that links words or larger constituents without syntactically subordinating one to the other and expresses a semantic relationship between them, 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, 'INTJ': An interjection is a word that is used most often as an exclamation or part of an exclamation, 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, 'PART': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, 'PUNCT': Punctuation marks are non-alphabetical characters and character groups used in many languages to delimit linguistic units in printed text, 'SCONJ': A subordinating conjunction is a conjunction that links constructions by making one of them a constituent of the other. The subordinating conjunction typically marks the incorporated constituent which has the status of a (subordinate) clause, 'SYM': A symbol is a word-like entity that differs from ordinary words by form, function or both, 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.
Teacher: Now, understand the problem? Solve this instance: Sentence: Then I got a bill for {{ $ }} 483.00 .
Word: $
Student: | [
0.7854921817779541,
0.06906075775623322,
-0.13932320475578308,
0.048850759863853455,
-0.04707604646682739,
-0.6568515300750732,
0.8393454551696777,
0.8631030917167664,
-0.32484596967697144,
-0.1653541773557663,
0.05466938763856888,
0.20399244129657745,
-0.6021342277526855,
0.39338231086730... |
TASK DEFINITION: In this task, you are given a list. This list contains many lists of integers. The list is several items written within a []. Your task is to find the maximum number among the members of each inner list. The output should be a list comprised of the maximums with the same order as the internal lists.
PROBLEM: [[-65, -132, -105, 40, 32, 84], [-53, -33]]
SOLUTION: [84, -33]
PROBLEM: [[-89, -60], [75, -56]]
SOLUTION: [-60, 75]
PROBLEM: [[-193, -73, 73, -84, 7, -19], [-111, 26, 56, 1, 1, 87, 37], [76, -35, -84, -177, -88], [-38, 25, -56, -45, -50, -94], [65, 62, -175, -174, 28, -22], [82, -179, -149], [81, -44, -132, -13], [-178, -131, -101, -9, -182, -49]]
SOLUTION: | [
0.6097791194915771,
-0.06425358355045319,
-0.748360276222229,
-0.16443566977977753,
0.21527676284313202,
0.35415151715278625,
1.1561694145202637,
0.5982286930084229,
-0.14778847992420197,
0.18025386333465576,
-0.5764176845550537,
0.3924812078475952,
-0.40564948320388794,
0.2216536849737167... |
Given the task definition and input, reply with output. 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, feel what is mentioned in the Tail or not. Feelings in this task are the emotional reactions on the part of PersonY or other participants in an event. For example, as a result of gift-giving, others (in this case, PersonY) might feel appreciated. 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.
Head: PersonX achieves PersonX's ___ by means<sep>Tail: hardworking
| [
-0.11115194857120514,
0.05908593162894249,
0.5873011350631714,
-0.08487963676452637,
-0.3151826858520508,
-0.642215371131897,
1.0884439945220947,
0.49227744340896606,
-0.3352798819541931,
-0.30688604712486267,
-0.4059229791164398,
-0.09650690853595734,
-0.9032158255577087,
0.35505682229995... |
In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write an implausible POS tag to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb
Input: Consider Input: What is the part-of-speech tag of the word "Taking" in the following question: How old was the musician with the record Taking Chances when she became well known ?
Output: NNS
Input: Consider Input: What is the part-of-speech tag of the word "to" in the following question: What degree did the special assistant to the president at the University of Utah receive ?
Output: JJ
Input: Consider Input: What is the part-of-speech tag of the word "known" in the following question: For the college who athletic teams were known as the Hilltoppers , how many colleges had a lower overall score ?
| [
0.49321651458740234,
0.6248981952667236,
-0.37521153688430786,
0.4546184241771698,
-0.05126902461051941,
-0.8926386833190918,
0.9212049245834351,
0.7575615644454956,
-0.711716890335083,
0.08575692027807236,
-0.7148053646087646,
0.30502748489379883,
-0.4915924072265625,
-0.0957380086183548,... |
You will be given a definition of a task first, then some input of the task.
In this task, you will be shown a passage. You need to write a fill-in-the-gap question based on your understanding of the events that might be inferred from the passage. Your question should be answerable based on the passage and only have one correct answer. Show the gap in your question with a _ .
From avoiding relegation on the final day of the season (twice!) to beating city rivals Liverpool to fourth spot a decade ago, Everton's 23 seasons of Premier League football have been varied to say the least. Roberto Martinez's men could only manage a disappointing 11th place finish last term, but would any of the current crop make it into the Toffees' all-time XI? Here, Sportsmail looks back over the Premier League era to pick the very best players to have worn the club's famous royal blue jersey. His best years may have been behind him at the Premier League's inception in 1992 but Southall remains the finest goalkeeper in the club's 137-year history.Four current Everton players make our greatest Premier League XI1995 FA Cup winners Neville Southall and Dave Watson are includedNo place for Wayne Rooney, Thomas Gravesen or Gary SpeedDuncan Ferguson leads the line with support from Tim Cahill
Output: | [
-0.2020825445652008,
0.21057242155075073,
0.11559491604566574,
0.11583679914474487,
0.6358169317245483,
-0.673668622970581,
0.17230939865112305,
0.70334392786026,
0.31676578521728516,
-0.012569084763526917,
-0.1849430948495865,
0.6507576107978821,
-1.1003211736679077,
-0.11034698039293289,... |
In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.
One example: Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.
Solution is here: 1
Explanation: The candy may or may not be popular and the first choice is correct. Based on the statement, candy doesn't melt and there's four stories of memorabilia dedicated to a candy. So the second choice agrees with the statement and the third choice disagrees with the statement.
Now, solve this: Statement: I have seen in my public and private sector careers how GPRA's purposes of improved performance and accountability can be achieved through the disciplined application of the goalsetting, planning, performance measurement, and reporting requirements of the act. Choices: 1. However it will take millions of dollars to achieve this school. 2. I can see how GPRA's improved performance can be achieved. 3. I have no public or private sector career experience.
Solution: | [
-0.072891965508461,
0.040852442383766174,
0.36855781078338623,
-0.06490398198366165,
0.4649905264377594,
-0.6664019823074341,
-0.2774864435195923,
0.9314545392990112,
0.207387775182724,
0.0076176468282938,
-0.3524209260940552,
-0.16901537775993347,
-0.2785608470439911,
-0.736878514289856,
... |
Detailed Instructions: You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Japanese.
See one example below:
Problem: A ideia é muito, muito simples.
Solution: このアイデアはとてもシンプルで
Explanation: The Portugese sentence is correctly translated into Japanese, because the meaning is preserved.
Problem: Portanto, estamos a trabalhar por fazermos boas imagens. Ponto final.
Solution: | [
-0.47464388608932495,
0.6299676299095154,
0.10541178286075592,
-0.6004076600074768,
-0.05143227055668831,
-1.126760721206665,
0.22908425331115723,
0.43890440464019775,
0.48356905579566956,
-0.4038219451904297,
-0.8447548747062683,
-0.011646784842014313,
-0.7742034196853638,
0.4956917166709... |
In this task, you are given two strings A, B. Find the longest common substring in the strings A and B.
euQWhCovKplukMYznXcD, XAfMhKdzhCovKplukMcMlSuBw
hCovKplukM
vMsEJRoLkWcmkuwNRz, ZmoLkWcmVZiBv
oLkWcm
wFeqOk, dBeqFP
| [
0.38302695751190186,
1.0225242376327515,
0.1039055585861206,
-0.4407605528831482,
-0.6985971927642822,
0.22606760263442993,
0.5447208881378174,
-0.34174400568008423,
-0.16641508042812347,
-0.821220874786377,
-0.49639973044395447,
-0.7242891788482666,
-0.34089526534080505,
0.151192873716354... |
TASK DEFINITION: In this task, you're given a context, a question, three options, and an answer. Your task is to classify whether the given answer is correct or not by providing 'Yes' or 'No', based on the context with commonsense reasoning about social situations.
PROBLEM: Context: Addison visited the pet store as it was about to close in half an hour.
Question: What will Addison want to do next?
Options: (A) hurry up browsing (B) get dressed to go out (C) leave their house
Answer: A
SOLUTION: Yes
PROBLEM: Context: Remy represented Skylar's interests while they were away on vacation.
Question: How would Remy feel afterwards?
Options: (A) like a bad friend (B) irresponsible (C) responsible
Answer: C
SOLUTION: No
PROBLEM: Context: Cameron works in Human Resources, has been doing interviews all week, and finally hired a new worker.
Question: Why did Cameron need to do this?
Options: (A) have help at work (B) find a different job (C) go home
Answer: A
SOLUTION: | [
0.08611488342285156,
0.08633176982402802,
0.20155039429664612,
-0.016396012157201767,
0.0020431659650057554,
-0.03246200829744339,
0.21166546642780304,
0.9472875595092773,
0.2462029904127121,
0.4278287887573242,
0.21950042247772217,
0.505364179611206,
-0.3562770485877991,
-0.41999673843383... |
In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: obscene and non-obscene. A comment is obscene if it is considered offensive to the public sense of decency, for example because it too obviously relates to sex or contains language regarded as taboo in polite usage.
Example input: Comment: Damn! Another cloudy day, and it's all Obama's doing!
Example output: Obscene
Example explanation: This is obscenity because it hints on sexual content that is offensive to the public sense of decency.
Q: Comment: The US government should not be investigating people making jokes or trying to criminalize laughter. They see fit to go after a comedian for saying “c**k” on TV while remaining silent about the man in the Oval Office who once bragged that he could “grab them by the p***y”.
For those who are complaining, apparently it's only about free speech if it adheres to your belief system.
A: | [
-0.8680710196495056,
0.7993097901344299,
0.5543840527534485,
-0.7473222613334656,
0.4785960018634796,
-0.35425418615341187,
0.23885977268218994,
0.25407564640045166,
0.11188614368438721,
0.3011818528175354,
-0.4241730570793152,
-0.3939162492752075,
-0.32608240842819214,
-0.7402826547622681... |
You are given an original reference as well as a system reference. Your task is to judge the informativeness of the system reference. If the utterance provides all the useful information from the meaning representation output 1, else output 0.
[EX Q]: System Reference: x is a restaurant in the riverside area.
Original Reference: x is a restaurant near the river.
[EX A]: 1
[EX Q]: System Reference: are you looking for a expensive or cheap price range is no restaurant?
Original Reference: would you like expensive or cheap food?.
[EX A]: 0
[EX Q]: System Reference: what area are you looking for a hotel in?
Original Reference: is there any area of the city you would prefer?.
[EX A]: | [
-0.7536836862564087,
0.8033093810081482,
-0.7965001463890076,
-0.25120028853416443,
-0.6691316366195679,
-0.7559424638748169,
1.1479744911193848,
0.7419737577438354,
0.03474719822406769,
-0.42499488592147827,
-0.12672077119350433,
-0.39984506368637085,
-0.2870813012123108,
-0.1973931789398... |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
A text is given in Malayalam. Translate it from the Malayalam language to the Panjabi language. The translation must not omit or add information to the original sentence.
ਪੱਛਮ ਤੋਂ ਪੂਰਬ ਤੱਕ ਊਰਜਾ ਖਪਤ ਵਿੱਚ ਇੱਕ ਤਬਦੀਲੀ ਆਈ ਹੈ।
Solution: പടിഞ്ഞാറ് നിന്ന് കിഴക്കോട്ട് energy ർജ്ജ ഉപഭോഗത്തിൽ മാറ്റം വരുത്തിയിട്ടുണ്ട്.
Why? Correct translation for given sentence. Input sentence means 'There has been a change in energy consumption from the west to east.' which is the same as the output sentence.
New input: ਰਾਸ਼ਟਰਪਤੀ ਨੇ ਸ਼ਰਾਬ ਅਤੇ ਨਸ਼ੀਲੇ ਪਦਾਰਥਾਂ ਦੇ ਦੁਰ-ਵਰਤੋਂ ਦੀ ਰੋਕਥਾਮ ਵਿੱਚ ਸ਼ਾਨਦਾਰ ਸੇਵਾਵਾਂ ਲਈ ਰਾਸ਼ਟਰੀ ਪੁਰਸਕਾਰ ਪ੍ਰਦਾਨ ਕੀਤੇ
Solution: | [
0.4184437394142151,
0.9142286777496338,
0.09917186200618744,
-1.006841778755188,
-0.46574366092681885,
-1.0629873275756836,
0.5326769351959229,
0.49478089809417725,
-0.07943315804004669,
-0.05872421711683273,
-0.47988802194595337,
-0.40822315216064453,
-0.5018774271011353,
-0.3131998181343... |
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: DOWN EASTERS
Clue: The governor's mansion in this capital city was formerly the home of James G. Blaine
| [
-0.6532217264175415,
0.9312292337417603,
-0.10122548043727875,
-0.2377815842628479,
0.35245025157928467,
-0.41378235816955566,
0.7467470169067383,
-0.12585990130901337,
-0.05885814130306244,
0.15488660335540771,
-0.24090668559074402,
0.5299886465072632,
-0.42921388149261475,
-0.34479740262... |
Detailed Instructions: In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the alphabetical elements in the given list. Return 0 if no alphabetical element in the list
Problem:['3911', '3857', 'U', 'S', '8155', '6083', '3075', 'e', '3171', '7951', 'h', '8689', 'Q', 's', 'Y', '4805', 'n', 'R', '9661', 'o', 'o', 'z', '1949', '3887', 'S', '995', 'v', 'X', 'z', '7493', 'r', '9449']
Solution: | [
-0.09848932921886444,
0.9136442542076111,
-0.014575294218957424,
-0.33587199449539185,
0.04773645102977753,
-0.47927457094192505,
0.7850502133369446,
0.01909162662923336,
-0.6133102178573608,
0.33355048298835754,
-0.3373314142227173,
0.4765147268772125,
0.4640730619430542,
0.15561431646347... |
Teacher:In this task, you will be presented with a question in Dutch language, and you have to write the location names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Identifier used for the location name - LOC. . There can be instances with no location name entity, then return 'None'.
Teacher: Now, understand the problem? Solve this instance: Ik ben professioneel genoeg om te beseffen dat een verlies tegen Agassi , die meer begiftigd is dan mij , geen drama hoeft te zijn . "
Student: | [
0.2739902436733246,
0.07037126272916794,
0.17685836553573608,
-0.34035342931747437,
-0.08759135007858276,
-0.19017697870731354,
0.4347100555896759,
0.1950560063123703,
0.6382889747619629,
-0.7589097023010254,
-0.2922305762767792,
0.35254621505737305,
-0.1262548416852951,
-0.141530811786651... |
Definition: In this task, you are given a sentence in the English language and your task is to convert it into the Hindi language. In translation, keep numbers as it is.
Input: Milestones include a roll out of first aircraft by 1995 and first flight by 1996 .
Output: | [
0.11003581434488297,
0.19839850068092346,
-0.09171085059642792,
0.06481310725212097,
0.17325150966644287,
-0.0669575035572052,
-0.17501753568649292,
0.5905652046203613,
-0.30390995740890503,
0.012368232943117619,
-0.580341100692749,
0.05446154996752739,
-0.4651632606983185,
0.2193792611360... |
Part 1. Definition
In this task you will be given an arithmetic operation and you have to find its answer. The operators '+' and '-' have been replaced with new symbols. Specifically, '+' has been replaced with the symbol '@' and '-' with the symbol '#'. You need to perform the operations in the given equation return the answer
Part 2. Example
6 @ 17
Answer: 23
Explanation: Here, '@' represents the addition operation. So, the answer is 23 (6+17=23).
Part 3. Exercise
5324 # 6093 # 8720 @ 7431 @ 1499 # 560
Answer: | [
0.15320220589637756,
0.5328245162963867,
-0.7161059379577637,
-0.15473124384880066,
-0.41727346181869507,
-0.27726495265960693,
0.954869270324707,
1.386836051940918,
0.8323137760162354,
-0.011290602385997772,
-0.47304049134254456,
-0.4690456986427307,
-0.09114105999469757,
-0.0080127064138... |
In this task, you need to answer the given multiple-choice question on the physics. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.
Problem: a train 240 m long passed a pole in 24 sec . how long will it take to pass a platform 650 m long ? a . 65
Options: a ) 28 sec , b ) 89 sec , c ) 85 sec , d ) 16 sec , e ) 15 sec | [
0.6765203475952148,
0.1530887931585312,
-0.5483412742614746,
-0.12993209064006805,
-0.4468728303909302,
-0.3396194577217102,
-0.279450923204422,
0.245937779545784,
-0.30797260999679565,
-0.5746588110923767,
-0.742408037185669,
0.48747488856315613,
0.4476902484893799,
-0.03246695548295975,
... |
You are given a short poem which is written by a kid. Your task is to predict if the kid is in elementary school or high school. Anyone who is from grade 1st to 6th-grade will be considered as in elementary school, and 7th to 12th-grade kids will be considered as in high school. There are only two possible outputs, i.e., elementary and high. All inputs have at least one output and it cannot have both categories at a time.
swirly pink and blue big and small too sweet and sour bubblegum or no bubblegum still yummy lollipop | [
-0.6638623476028442,
1.2188559770584106,
0.6800640821456909,
-0.3074193000793457,
-0.384653240442276,
-0.32878515124320984,
-0.015065707266330719,
0.25416022539138794,
0.38753604888916016,
-0.9221169352531433,
-0.059453029185533524,
0.4292687177658081,
0.3314073383808136,
-0.13977998495101... |
Q: In this task, you need to answer the given multiple-choice question on geometry. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.
Problem: the perimeter of an equilateral triangle is 60 . if one of the sides of the equilateral triangle is the side of an isosceles triangle of perimeter 65 , then how long is the base of isosceles triangle ?
Options: ['a ) 10', 'b ) 15', 'c ) 20', 'd ) 25', 'e ) 30']
A: | [
0.5585912466049194,
0.18976238369941711,
-0.6552274823188782,
-0.8275243043899536,
-0.1607459932565689,
-0.828707218170166,
0.7616274356842041,
0.009350818581879139,
0.1604427993297577,
0.5213738679885864,
-0.7930406332015991,
0.6587838530540466,
-0.34271305799484253,
-0.5074111223220825,
... |
Part 1. Definition
In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long.
Part 2. Example
For many Brazilians, Michel Temer's ascension to president was surprising. But as the first Brazilian president to have charges brought against him while in office, his arrest is less unexpected.
Answer: Michel Temer: Brazil's arrested former president
Explanation: The output is a relevant title for the given passage as it highlights the main crux of the given text.
Part 3. Exercise
Police have said no trace of a powerful and potentially fatal painkiller has been found in heroin seized in the Borders.
Answer: | [
0.2557221055030823,
0.6584190130233765,
-0.16035453975200653,
-0.28312134742736816,
-0.13792654871940613,
0.056377895176410675,
-0.08815761655569077,
0.9407785534858704,
0.09567795693874359,
0.318448930978775,
-0.9237807989120483,
0.36246415972709656,
-0.6968188881874084,
-0.42660257220268... |
You are given a mathematical question described with a circumscribed mathematical vocabulary. Questions in this task usually contain some variables (e.g. X, Y), equations (e.g. X+Y=3) and some relationships (X is greater than Y). Often you need to find the value of the variable using equations and relationships. You are also given 4 or 5 answer options (associated with "A", "B", "C", "D", "E"). Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D', 'E'. LaTeX mathematical format (the standard way to express mathematical expressions in the typesetting software known as LaTeX) is used to express equations. Each question is solvable with high school math knowledge. Give only one answer for each question.
Example Input: 10 is what percent of A?
(A)\(10A\%\) (B)\(\frac { 1 } { 10A } \%\) (C)\(\frac { 10 } { A } \%\) (D)\(\frac { 100 } { A } \%\) (E)\(\frac { 1000 } { A } \%\)
Example Output: E
Example Input: If \(2^ { a + b } = 8\) and \(3^ { a - b } = 81\), what is the value of \(a\)?
(A)2 (B)3.5 (C)6 (D)8.5 (E)10
Example Output: C
Example Input: If \(6a = 48\) and \(ab = 1\), what is the value of b?
(A)\(\frac{1}{48}\) (B)\(\frac{1}{8}\) (C)\(\frac{1}{6}\) (D)6 (E)8
Example Output: | [
0.3473931550979614,
0.321309357881546,
-0.8379505276679993,
0.010247433558106422,
-0.22382254898548126,
-0.33072227239608765,
1.1683269739151,
1.3958115577697754,
0.529334545135498,
-0.5308597087860107,
-0.6349029541015625,
0.3069228231906891,
-0.06357171386480331,
-0.005746754352003336,
... |
Definition: Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., "survival" and "survive" are valid overlapping words. Little words like "the" or "of" don't count! You must generate significant words which are not the stop words.
Input: Sentence1: Warmer air has already led to melting glaciers.
Sentence2: warmer air forms boulders sometimes.
Output: | [
-0.003623201511800289,
0.5855997204780579,
0.288640558719635,
-0.38256242871284485,
0.1010296493768692,
-0.15914148092269897,
0.7466650605201721,
0.04935738071799278,
0.13738878071308136,
-1.0128977298736572,
-0.8498035669326782,
-0.3749889135360718,
-0.9929589033126831,
0.4860571622848511... |
Instructions: Given a sentence in Chinese, generate a new Chinese 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: 在消费者博客上, 储蓄是关键,
Output: | [
-0.3324058949947357,
0.05175987258553505,
-0.10497292876243591,
-0.5358248949050903,
0.10293974727392197,
-0.6458930969238281,
0.023103147745132446,
0.7601786255836487,
-0.18994560837745667,
-0.2229974865913391,
-0.5247094631195068,
-0.00812960509210825,
0.06255742907524109,
0.153055608272... |
Given the task definition and input, reply with output. The provided files include famous book titles and sentences in the English language, and we ask you to translate those to the Swedish Language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and form of each sentence in the Swedish language. 2) Also names ,dates and places should be preserved it should not get translated.
Slowly against the swift current they work their ponderous way, till, with a low grumble, they grate against the bank of the little island that from this day will bear the name of Magna Charta Island.
| [
-0.3844517767429352,
1.1753541231155396,
0.10673080384731293,
-1.1925194263458252,
0.04697195440530777,
-0.9225698709487915,
1.0861774682998657,
-0.4515986144542694,
0.30677908658981323,
-0.6822481155395508,
0.6263644695281982,
0.705596387386322,
-0.4907585680484772,
-0.1706375777721405,
... |
In this task, you are given a sentence containing a particular emotion. You must classify the sentence into one of the six emotions: 'joy', 'love', 'anger', 'fear', or 'surprise'.
One example is below.
Q: i am ever feeling nostalgic about the fireplace i will know that it is still on the property
A: love
Rationale: The word "nostalgic" could either indicate "love" or "sadness", but the fact that it is still on the property eliminates "love".
Q: i completely feel sympathetic for my children that suffer mentally because life is just too over stimulating
A: | [
-0.387077659368515,
0.2488287389278412,
0.31113243103027344,
-0.34768494963645935,
0.1455741673707962,
-1.1369335651397705,
1.728569746017456,
0.6169827580451965,
0.09014704078435898,
-0.3837641477584839,
-0.36464959383010864,
0.20494338870048523,
-1.270190715789795,
0.19008886814117432,
... |
Detailed Instructions: In this task, you are given commands (in terms of logical operations) and natural interpretation of the given command to select relevant rows from the given table. Your job is to generate a label "yes" if the interpretation is appropriate for the command, otherwise generate label "no".
Here are the definitions of logical operators:
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.
See one example below:
Problem: Command: eq { hop { nth_argmax { all_rows ; attendance ; 3 } ; competition } ; danish superliga 2005 - 06 }, interpretation: select the row whose attendance record of all rows is 3rd maximum. the competition record of this row is danish superliga 2005-06.
Solution: yes
Explanation: Here, the command and interpretion given for the command is correct that 3rd maximum should be selected from given table rows. Hence, the label is 'yes'.
Problem: Command: most_eq { all_rows ; home ; philadelphia }, interpretation: the average of the to par record of all rows is -5.6 .
Solution: | [
-0.1254892349243164,
-0.17132824659347534,
-0.32489264011383057,
0.5596597194671631,
0.4205425977706909,
-0.6299186944961548,
0.15473316609859467,
0.562041699886322,
0.17263129353523254,
0.0591047927737236,
-0.3495001792907715,
0.44563278555870056,
0.08393445611000061,
0.4949273467063904,
... |
Detailed Instructions: In this task, you are given an input i,A where i is an integer and A is an array. You need to find every ith element of A starting with the 1st element.
See one example below:
Problem: 3, ['a', '34', 'f', '931', '7', '3432', '13245', '762']
Solution: a, 931, 13245
Explanation: Here, every 3rd element from array are 'a', '931', and '13245'.
Problem: 7, ['9381', '3627', 'C', '5565', '8749', '885', 'L', '7719', 'k', '581', '139', '4951', '1159', 'd', '689', 'Z', '6899', '3665', 'c', '4223', '8335', '2043', '8575', '4037', 'F', 'O', 'V', 'y', 'b', '9083', '7183', 'n', '9565', '8899', 'L', '2909', '7879']
Solution: | [
0.19503721594810486,
-0.15994051098823547,
-0.5437312126159668,
-0.6726887226104736,
-0.4290294051170349,
-0.27268731594085693,
0.5590450763702393,
0.3968997001647949,
-0.43631935119628906,
-0.28689900040626526,
-0.5977726578712463,
0.14187997579574585,
0.07504157721996307,
0.1479962170124... |
Part 1. Definition
Generate an appropriate single-sentence summary for the given text such that it includes the main topic of the text.
Part 2. Example
By Marianna SpringSpecialist disinformation reporter, BBC News The adverts show the Democratic Party challenger with an earpiece, and say that he refused to have his ears checked for devices prior to the debate. The Biden campaign rejected the claims. The Trump campaign adverts ask: "Why won't Sleepy Joe commit to an ear test?" and "Who is in Joe's ear?" Accusations that presidential candidates have received debate help via hidden hearing devices are familiar, albeit unproven. Such allegations have been levelled against both Republican and Democratic candidates in the past. Prior to Tuesday's debate, the rumour about Mr Biden's supposed earpiece was circulating on several social networks, and was being promoted by the Trump campaign. At least 15 versions The advertising campaign was launched after the debate, and also promotes two other baseless but widely shared rumours about Mr Biden. One suggested he asked for breaks during the debate, and another accused him of refusing a "drug test". The photo featured in the advert is not from Tuesday's debate. It was first shared online in September 2019. In a number of the adverts, it has been doctored to show Mr Biden wearing wireless Apple headphones. This was not the case in the original image. Some versions circle the ear featuring the headphone. By Wednesday evening, there were at least 15 different versions of the advert, and according to Facebook's Ad Library, they had reached at least 10 million users. Facebook has pledged to label posts containing voting misinformation and point users towards accurate information ahead of the election. However its policy does not involve fact-checking political speech, including in advertisements. The company declined to comment about the latest Trump ad campaign. Rumour origins Hours before the debate, the claims went viral on Facebook and YouTube. Identical memes were pushed by a number of popular Facebook pages with names such as US Conservative and Unhinged Left. They claimed "Joe Biden should be inspected for a hidden earpiece as well as submit to a drug test before the debate". These memes are subject to fact-checks - and some have had warning labels applied to them on Facebook. The claims were picked up by Fox News and other conservative news outlets. They were further amplified by supporters of QAnon, an unfounded a conspiracy theory that claims President Trump is fighting a secret war against elite Satan-worshipping paedophiles. Those who believe in QAnon are known for promoting political disinformation on social media which targets opponents of the president. They shared close-up pictures of Mr Biden's ears, alleging a listening device was visible. During the debate, some also shared photos of a fold in Mr Biden's shirt, claiming it was caused by a wire, and of a supposed device on his wrist, where he wears a rosary in memory of his late son Beau. Nothing new Conspiracy theories about secret listening devices have been recycled in presidential election campaigns for the past two decades. Democratic candidate Hillary Clinton faced similar unfounded claims ahead of the 2016 presidential election. In 2004, rumours circulated among left-wing sites and blogs that President George W Bush was being aided by a secret earpiece. None of those allegations were found to be true. Even if a candidate did wear an earpiece, any advantage would be questionable. As TV and radio presenters can attest, listening to someone while simultaneously talking during the back-and-forth of a live event is a difficult skill to master.
Answer: US President Donald Trump's re-election campaign is running hundreds of Facebook advertisements pushing an unfounded conspiracy theory that Joe Biden cheated during the first US presidential debate.
Explanation: This is a relevant summary for the given paragraph. It also contains explicit phrases from the given text
Part 3. Exercise
"I don't sleep very well anyway but, after the horrific scenes at Grenfell, I just lay in bed thinking about it quite a lot," he said. "Yeah, replacing [the cladding] would be a massive cost. But what comes first, money or lives?" At least 80 people are believed to have died after a huge fire engulfed Grenfell Tower in west London on 14 June. Cladding put on the building in 2015 is suspected to have spread the fire in the 24-storey block in North Kensington, which started in a fridge. Shortly after the blaze, the government ordered tests on cladding on all tower blocks in the UK. A number of high-rises, including in Cambridgeshire, London, Newcastle, Sheffield, Sunderland, Manchester and Salford, failed the tests. This included Canon Hussey Court. Mr Nolan remembers seeing the "horrific events" at Grenfell unfolding on television while he was on holiday in Turkey. "Straight away I was thinking of my flat and what the future holds for me when I get back to the UK. "When I got home I phoned up Salix, my home provider, and they tried to reassure me that everything they could do would get done as soon as possible." In the weeks that followed the Grenfell Tower fire, Salix Homes began removing cladding from its high-rise flats, including at Canon Hussey. But the housing association halted the work in July citing "unclear government advice". 'It's scary' Three months later, Mr Nolan and his neighbours are still waiting for action to be taken. "I thought they were going to take it all off at that time but it's obvious with the insulation underneath they can't," he said. "Nobody knows if [the cladding] is going to be off in six months or six years, we don't have a clue. "So we're just in limbo and it's a frightening limbo to live in." Another Canon Hussey resident, who does not want to be identified, said she suffers from anxiety attacks and worries that she would not be able to get out in the event of a fire. "My main concern is I would never be found, like them poor people, you know that perished. "We're stuck in this and it's scary, it frightens me. "This cladding really needs to come off. I don't understand why they won't take it off because other organisations are. Why are these not doing it?" Salford City Council is one of those other organisations. As freehold owner of nine blocks in Salford which failed safety tests, it has already started to replace the cladding at a cost of up to £25m. But many private housing associations are yet to make plans to do the same. Salix Homes said it was now getting "some clarity" following government testing on the "safest and most appropriate" types of systems to replace the cladding with. The company said it was taking advice from "technical experts" and would carry out the work "as quickly as possible" but "could not provide clear timescales". Round-the-clock security, additional patrols and new fire alarms had already been introduced and safety was its "utmost priority", it added. A total of 32 tower blocks in Salford have been deemed unsafe after the testing, along with 30 in Manchester, two in Oldham, three in Stockport and six in Trafford. Salford City Mayor and head of the Greater Manchester High Rise Task Force, Paul Dennett criticised the government's response saying it was "kicking things into the long grass" by waiting for the outcome of the Grenfell Public Inquiry. "These residents can't wait for that, they want solutions now, they want solutions yesterday...the government need to be providing some interim solutions for the blocks that have failed up and down the country," he said. 'Feel safe' A Department for Communities and Local Government (DCLG) spokesperson said public safety was "paramount", which is why it commissioned fire safety tests and published guidance. Secretary of State Sajid Javid told the Commons in June that the government would try and assist local councils and housing associations which could not afford to remove failed cladding from tower blocks. But the DCLG spokesperson said, while local authorities can seek assistance, it is the responsibility of building owners to ensure their properties are safe and it's up to them to fund fire safety measures. Mr Nolan said he would only feel safe when the cladding was replaced. "I love my Salford... I've finally got a home for 15 years that I'm proud of, so I don't want to move, I just want to feel safe." Inside Out North West is on BBC One in the North West at 19:30 BST on Monday 23 October and later on BBC iPlayer for 30 days.
Answer: | [
0.21378695964813232,
0.5666708946228027,
-0.41306406259536743,
-0.12408678978681564,
0.19182467460632324,
-0.22997474670410156,
0.6392524242401123,
1.1235692501068115,
-0.3391091227531433,
0.17494206130504608,
-0.06783907115459442,
0.4876718521118164,
-0.5224305987358093,
0.150665611028671... |
Given a sentence in the Lao, provide an equivalent translation in Japanese that retains the same meaning through the translation. In translation, keep numbers as it is.
Ex Input:
ໄວລຸ້ນ ຜູ້ທີ່ຖືກກ່າວຫາ ວ່າຍິງລູກລະເບີດໃສ່ຕໍາຫລວດ ແຕ່ວ່າ ເຮັດໃຫ້ຕົວລາວເອງບາດເຈັບ.
Ex Output:
ティーンエージャーは警官に向かって手榴弾を投げたが、自分自身が傷ついた。
Ex Input:
"ພວກເຮົາບໍ່ຢ້ານນັກຂ້າ ເຖິງວ່າພວກມັນກຳລັງມ່ວນກັບ ການປ້ອງກັນຂອງປາມຸກລັດ."
Ex Output:
「我々は、例え国家元首の保護を受けている殺人者であっても、恐れはしない。」
Ex Input:
ມາໂຕສ ກຳລັງແຂ່ງຂັນຊິງຫຼຽນທອງກັບ ອາມານ ຊິລມາໂນບ ຈາກ ຄາຊັກສະຖານ ໃນຂະນະທີ່ກຳລັງຄຳ້ຊູອາການບາດເຈັບ.
Ex Output:
| [
-0.10048229992389679,
0.4093153476715088,
-0.6757315397262573,
-0.39937543869018555,
-0.18853303790092468,
-0.8165565133094788,
0.7792288064956665,
0.3448403477668762,
-0.12813767790794373,
-0.32685136795043945,
-0.8789867162704468,
0.7772284746170044,
-1.177610158920288,
0.362411558628082... |
Given the task definition and input, reply with output. This task is about translating a given English language sentence to Spanish.
Sebastian Mortelmans, Jacob Brody, Dave Heal, Azymnis,
| [
-0.37526461482048035,
0.7744842767715454,
0.16977541148662567,
-0.8151346445083618,
0.12330333143472672,
-0.6034033298492432,
0.06734734028577805,
-0.3848974108695984,
0.510448694229126,
-0.5824077129364014,
-0.007387056946754456,
0.4578493535518646,
-0.3668716549873352,
-0.428249955177307... |
Instructions: Given a sentence in Russian, generate a new Russian 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: Вам неудобно умирать в пустыне.
Output: | [
-0.141438826918602,
0.5846270322799683,
-0.3284907937049866,
-0.5640944242477417,
-0.9788079261779785,
0.10300532728433609,
0.8506271243095398,
1.0546375513076782,
0.2608654797077179,
-0.145783931016922,
-1.297264814376831,
-0.355093777179718,
-0.4278114438056946,
0.12657052278518677,
-0... |
Detailed Instructions: In this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.
Q: ['341', '7621', '1227', '5517', '1431', 'J', 'u', 'r', '129', 'U', 'h', 'Q']
A: | [
-0.5949820280075073,
0.2728744447231293,
0.4182767868041992,
-0.3755734860897064,
-0.21894913911819458,
-0.23406833410263062,
-0.07232914119958878,
0.05491099879145622,
-0.1237180307507515,
-0.3586609959602356,
-0.2781461477279663,
-0.103919118642807,
0.25716447830200195,
-0.25803428888320... |
In this task, you are given dvd product reviews in German language. The goal is to classify the review as "POS" if the overall sentiment of the review is positive or as "NEG" if the overall sentiment of the review is negative.
One example is below.
Q: Endlich . Endlich erscheint Staffel 2 auf DVD. Habe ewig darauf gewartet. Die Staffel 2 ist in meinen Augen die Beste, da man dort auch mehr von Mark Kellers super Stimme hört. Ein Wehrmutstropfen ist das Caroline Schröder, die Darstellerin der Bea nicht mehr dabei ist.
A: POS
Rationale: The overall sentiment of the review is positive as the reviewer refers to the dvd with positive expressions such as 'super Stimme hört'. Hence, the label is 'POS'.
Q: Maßlos entäuschend!! . Also es fällt mir schon sehr schwer, nur ein gutes Haar an dieser DVD zu lassen. Daher komme ich gleich zum einzigen positiven Punkt dieser DVD. Man darf sich an einigen seltenen Orginalaufnahmen erfreuen und auch eine sehr schöne aufnahme der "Black 6" aus England aus einem Begleitflugzeug in Farbe mit tollem Db605 Sound ist dabei. Aber einem echten Bf109 Liebhaber ist es fast unmöglich sich den Kommentar der DVD zu gemüte zu führen. Die Bilder passen sehr selten zu dem Kommentar. Man sieht G Versionen wärend gerade über die Einsätze der Legion Condor in C Versionen gesprochen wird. Desweiteren hat man das Gefühl, dass die Autoren der DVD keine Ahnung von der Messerschmitt hatten. Falsche Waffen, falsche Motoren und falsche Erkennungsmerkmale werden in alle möglichen Versionen "gewurschtelt" so dass man in die Fernbediehnung beißen möchte. Nach der kurzen Anmerkung das es eine G Version gab wird der Rest der Entwicklung mit dem Satz abgehandelt: "Dann kamen noch K, H und T Varianten" Keine nähere Erläuterung?! Bis auf die bewegten Bilder ist jedes Durchschnittsbuch um Welten besser, wenn es um die Versionen und die Technik geht.
A: | [
0.011884967796504498,
0.11048898845911026,
-0.3541693389415741,
0.10453440994024277,
0.26780155301094055,
0.05922143533825874,
1.062075138092041,
0.7982332110404968,
0.44435641169548035,
0.6085660457611084,
0.016425158828496933,
-0.24071598052978516,
-0.04255502671003342,
-0.24508351087570... |
Given the task definition and input, reply with output. In this task, you are given a sentence in the English language and your task is to convert it into the Hindi language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).
A collaboratively-developed operating system kernel known as GNU Hurd has been made bootable using the L4 microkernel, which provides room for significant speed improvements over an existing implementation using the Mach microkernel.
| [
-0.9078477025032043,
0.6315217018127441,
0.8009487390518188,
-0.10962014645338058,
-0.12002868205308914,
-0.27215576171875,
0.47974294424057007,
-0.0334269255399704,
-0.23364293575286865,
-0.5266475677490234,
-1.0410829782485962,
-0.42511966824531555,
-0.11059858649969101,
-0.0172563791275... |
Detailed Instructions: In this task, you will be given sentences in which your task is to recognize the name of the drug or medicine. Drugs are substances that change a person's mental or physical state. They can affect how your brain works, how you feel and behave, your understanding, and your senses. Although there might be several correct answers, you need to write one of them.
Q: Replicate brain magnetic resonance imaging examinations after six weeks and 11 months of penicillamine therapy documented the development of new brain lesions during this period, while liver biopsy specimen data disclosed that excellent hepatic decoppering had occurred.
A: | [
0.054214634001255035,
0.2450140416622162,
-0.12584084272384644,
-0.887122631072998,
-0.32753121852874756,
-1.1819343566894531,
0.6682393550872803,
0.5252450704574585,
0.30991655588150024,
-0.6720786094665527,
-1.0312228202819824,
-0.20665496587753296,
-0.7851985096931458,
0.553257167339325... |
Given a sentence in Hindi, generate a new Hindi 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.
[EX Q]: जीवित कलाकार की छवि वीडियो टेप पर कैप्चर की जा सकती है.
[EX A]: एक जीवित कलाकार की हँसी विडियो टेप पर की जा सकती है।
[EX Q]: अगर आप सिगरेट पीने के लिए छोड़ देते हैं तो आपको नाई की भेंट करनी चाहिए ।
[EX A]: आप एक बाल काटना चाहते हैं तो आप एक नाई उड़ जाना चाहिए.
[EX Q]: Cum मुंह में चला जाता है.
[EX A]: | [
-0.6027958393096924,
-0.25360533595085144,
0.5625718832015991,
-0.21914666891098022,
0.18277227878570557,
-0.6839379668235779,
-0.28299471735954285,
0.862979531288147,
-0.8166303038597107,
0.2364555150270462,
-0.40461739897727966,
-0.7511160373687744,
-0.09197543561458588,
0.32009318470954... |
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 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.
يمكنك أن تُسدّد محفظة بطاقة إئتمان لحمل كل بطاقات إئتمانك
Solution: يمكنك تحميل محفظة بطاقة إئتمان لحمل كل بطاقات إئتمانك.
Why? This is a good example of a change in the input. The created sentence is semantically similar to the input as both are talking about credit card wallets and the changes in the sentence follows the commonsense knowledge.
New input: « والشمس على الأرض قدير ».
Solution: | [
0.808465838432312,
0.3439638018608093,
-0.7569757699966431,
-0.7519601583480835,
-0.55687415599823,
-0.621462881565094,
1.3809657096862793,
0.4440925121307373,
0.6088027954101562,
-0.47899067401885986,
-0.09184498339891434,
0.0013105912366881967,
-0.49896636605262756,
0.4397735893726349,
... |
In this task, you are given an input stream, and your task is to produce a grammatically correct version of the input sentence. 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 grammatically correct version of the input stream. Stream words are in [] and have been separated with a comma. The sentence can contain words that have case, punctuation, stem-based, intra-word, and digit punctuation errors that need to be corrected. For example, the text should be uppercased/lowercased as per necessity (like the beginning of a sentence, proper nouns, etc.), and digits need to be normalized (6 as six and so on). Note that you don't need to normalize the years. You don't need to fully edit the sentences, if end of the input stream contains sentence fragments, keep them as is.
["we're", 'going', 'to', 'talk', 'about', 'a', 'really', 'powerful', 'way', 'to', 'analyze', 'circuits', 'called', 'the', 'node', 'voltage', 'method', 'and', 'before', 'we', 'start', 'talking', 'about', 'what', 'this', 'method', 'is', "we're", 'going', 'to', 'talk', 'about', 'a', 'new', 'term', 'called', 'a', 'node', 'voltage', 'so', 'far', 'we', 'already', 'have', 'the', 'idea', 'of', 'a', 'an', 'element', 'has', 'a', 'voltage', 'across', 'it', 'and', 'we', 'refer', 'to', 'that', 'as', 'a', 'an', 'element', 'voltage', 'or', 'if', "it's", 'part', 'of', 'a', 'circuit', 'and', "it's", 'a', 'branch', 'of', 'a', 'circuit', 'it', 'we', 'call', 'the', 'branch', 'voltage', 'and', "that's", 'a', 'voltage', "that's", 'associated', 'with', 'a', 'particular', 'element', 'so', 'now', 'we', 'have', 'the'] | [
1.0445892810821533,
0.5494542121887207,
0.12483614683151245,
-0.07268209755420685,
0.4912175238132477,
-1.073451042175293,
0.05389948934316635,
0.9294100999832153,
-0.2671796679496765,
0.6920427083969116,
-0.4422052502632141,
-0.3222501277923584,
-0.2968323826789856,
-0.4617137610912323,
... |
Instructions: In this task, you are given a review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer "yes" when the tweet has that particular sentiment, otherwise generate answer "no".
Input: Review: "The Kennel Murder Case" starts off at a run and doesn't stop until the very end. Everybody had reason to kill the victim, and several people tried. William Powell is terrific as Philo Vance, gentleman detective. Mary Astor is refreshing as the put-upon niece who only wants to marry her Scottish gentleman and enjoy her inheritance. This movie comes paired with "Nancy Drew, Reporter" on DVD, which is also fun. If you have to rent the disc (or check it out from your local library), do it. It's pure entertainment! Question: is it a negative review?
Output: | [
-1.4161125421524048,
-0.11328595876693726,
0.6148087382316589,
0.342102587223053,
0.14088378846645355,
0.127670556306839,
0.8500366806983948,
0.6515333652496338,
0.509271502494812,
0.26761966943740845,
-0.24154525995254517,
-0.10775063931941986,
-0.499570369720459,
-0.24857942759990692,
... |
Instructions: In this task, you are given a sentence in the Hindi language and your task is to convert it into the English language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).
Input: वाणिज्यिक लॉन्च के लिए उपयोग किए जाने के साथ-साथ, नए एलसी-40 का उपयोग नासा के साथ वाणिज्यिक ऑर्बिटल ट्रांसपोर्टेशन सर्विसेज (सीओटीएस) अनुबंध के तहत अंतर्राष्ट्रीय अंतरिक्ष स्टेशन तक कार्गो पुनःआपूर्ति मिशन के लिए किया जाएगा।
Output: | [
-0.6574559211730957,
0.8399733304977417,
0.08929413557052612,
0.0022562011145055294,
0.2594262361526489,
-0.04860517382621765,
0.48504185676574707,
0.3863043785095215,
-0.08080954849720001,
-0.2440306842327118,
-0.330348938703537,
0.16033299267292023,
0.29731547832489014,
-0.23136292397975... |
Teacher:In this task, you are given a sentence which is either in the Swedish language or English language. You task is to identify the language of input sentence. Input sentence can be in Swedish or English language only and also it cannot have two languages at a time.
Teacher: Now, understand the problem? Solve this instance: Vi anser alla att konkurrens är nödvändig för ekonomin och främjar prestationsförmågan, och jag tror att vi också bör släppa in konkurrens i regionerna.
Student: | [
-0.8237658143043518,
0.8343589305877686,
0.9714383482933044,
-0.7364310026168823,
0.3366166949272156,
-0.07921390980482101,
0.2972373366355896,
0.8310607671737671,
0.6530241370201111,
-0.704005777835846,
-0.16876043379306793,
0.21965256333351135,
-0.3954881429672241,
-0.6924555897712708,
... |
You will be given a definition of a task first, then some input of the task.
In this task, you need to reverse all words of a given length in the sentence. The number of letters in a word determine its length. For example, the length of the word "apple" is 5.
Sentence: 'a cat jumping off of a truck with containers of bottles'. Reverse all words of length '7' in the given sentence.
Output: | [
-0.5882880687713623,
0.6345984935760498,
0.2457909882068634,
0.09266389906406403,
0.12231381237506866,
-0.2812240719795227,
0.09357142448425293,
0.3346603512763977,
-0.10660240799188614,
-0.4646484851837158,
-1.0009478330612183,
-0.12012508511543274,
-0.6962782144546509,
0.2472205758094787... |
Instructions: In this task, you're expected to write answers to questions involving multiple references to the same entity. The answer to the question should be unambiguous and a phrase in the paragraph. Most questions can have only one correct answer.
Input: Passage: Few large stone buildings were constructed between the Constantinian basilicas of the 4th century and the 8th century, although many smaller ones were built during the 6th and 7th centuries. By the beginning of the 8th century, the Carolingian Empire revived the basilica form of architecture. One feature of the basilica is the use of a transept, or the "arms" of a cross-shaped building that are perpendicular to the long nave. Other new features of religious architecture include the crossing tower and a monumental entrance to the church, usually at the west end of the building.Carolingian art was produced for a small group of figures around the court, and the monasteries and churches they supported. It was dominated by efforts to regain the dignity and classicism of imperial Roman and Byzantine art, but was also influenced by the Insular art of the British Isles. Insular art integrated the energy of Irish Celtic and Anglo-Saxon Germanic styles of ornament with Mediterranean forms such as the book, and established many characteristics of art for the rest of the medieval period. Surviving religious works from the Early Middle Ages are mostly illuminated manuscripts and carved ivories, originally made for metalwork that has since been melted down. Objects in precious metals were the most prestigious form of art, but almost all are lost except for a few crosses such as the Cross of Lothair, several reliquaries, and finds such as the Anglo-Saxon burial at Sutton Hoo and the hoards of Gourdon from Merovingian France, Guarrazar from Visigothic Spain and Nagyszentmiklós near Byzantine territory. There are survivals from the large brooches in fibula or penannular form that were a key piece of personal adornment for elites, including the Irish Tara Brooch. Highly decorated books were mostly Gospel Books and these have survived in larger numbers, including the Insular Book of Kells, the Book of Lindisfarne, and the imperial Codex Aureus of St. Emmeram, which is one of the few to retain its "treasure binding" of gold encrusted with jewels. Charlemagne's court seems to have been responsible for the acceptance of figurative monumental sculpture in Christian art, and by the end of the period near life-sized figures such as the Gero Cross were common in important churches.
Question: What is lost except for a few crosses?
Output: | [
0.47650671005249023,
0.8636253476142883,
-0.6719651222229004,
-0.2625887989997864,
0.3509405255317688,
-0.5128253698348999,
0.287324458360672,
0.8402889370918274,
-0.2916479706764221,
-0.232282355427742,
-0.013601094484329224,
0.6657431125640869,
-0.7502254247665405,
0.19900387525558472,
... |
Instructions: You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. If the conversation begins with a question, label it '1' otherwise '0'.
Input: Person1: On Saturday night I ’ m going to have a small get-together .
Person2: Good .
Person1: Would you like to come ?
Person2: Do you mean this Saturday ?
Person1: Yes , this coming Saturday .
Person2: Thanks for inviting me , Jack , but I ’ Ve already made plans for this weekend . I won ’ t be able to come , I ’ m afraid .
Person1: I ’ m sorry to hear that .
Person2: Yeah , that ’ s too bad .
Person1: Well , perhaps , another time .
Output: | [
0.04047071933746338,
0.8381311893463135,
-0.04557529091835022,
0.13583117723464966,
-0.2935805320739746,
-0.8459190726280212,
0.4251934885978699,
0.13605830073356628,
-0.15670712292194366,
0.46774035692214966,
-0.22966954112052917,
-0.370625376701355,
-0.5384887456893921,
0.001100827823393... |
Given the task definition and input, reply with output. In this task, you will be presented with a text and a pronoun. You should write an implausible answer to the question of what is the pronoun's reference. Even though there exist multiple wrong answers, we only need a single wrong answer. Position of the pronoun in the text is showed within two "_"s.
Ananta, while coming from Bombay, accompanies a woman, Janaki, and keeps her as his mistress and enjoys romance. But she is slowly dying of Tuberculosis. Satyapal, Puran Bhagat Singh, and Ralia all play their role in the struggle against the capitalists in their own way. Ananta's Gandhian approaches are unwelcomed. Ralia, in _his_ utter madness kills Ananta, hitting his head against a machine repeatedly. <sep>, Pronoun: his
| [
-0.4082030951976776,
1.2278387546539307,
0.33305180072784424,
0.33347851037979126,
-0.4924654960632324,
0.12725746631622314,
0.6546193361282349,
0.6615684628486633,
0.36154958605766296,
-0.17974059283733368,
-1.1106982231140137,
0.5026425123214722,
-0.457863450050354,
0.20703019201755524,
... |
This task is to translate a news commentary given in Arabic language into Czech language. Translate the input statement into the output language while preserving the numberical values, special characters and context of the commentary done.
One example is below.
Q: الذهب بعشرة آلاف دولار؟
A: Zlato za 10\xa0000 dolarů?
Rationale: The translation has retained the exact meaning and is accurate.
Q: وبطبيعة الحال فإن عارضات الأزياء والمصممين الطامحين سوف ينظرون إلى موقع ويردروب باعتباره مكاناً لابد من استكشافه (تماماً كما أصبحت مواقع مثل ماي سبيس ويوتيوب من الأماكن التي يؤمها فنانو الأداء).
A: | [
-0.5847832560539246,
0.13800537586212158,
-0.598246157169342,
-0.02689085528254509,
-0.6726205348968506,
0.33779847621917725,
0.8413054943084717,
0.25512972474098206,
0.6951151490211487,
-0.7325827479362488,
-0.18068769574165344,
0.4316353499889374,
-1.2187613248825073,
0.2369484305381775,... |
Teacher:Given a sentence, generate a new 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.
Teacher: Now, understand the problem? Solve this instance: A fly can try to escape from a spider's web.
Student: | [
-0.7524154186248779,
0.8852763175964355,
0.2364664375782013,
-0.6274993419647217,
-0.14370426535606384,
-0.6454160213470459,
0.3876676559448242,
0.8650364279747009,
-0.09748978167772293,
-0.35539111495018005,
-0.5885748267173767,
0.6047829389572144,
-1.1903975009918213,
-0.2549736201763153... |
You are given a sentence in Polish. Your job is to translate the Polish sentence into Japanese.
[EX Q]: (Śmiech) JF: Chodzi mi o to, że takie zadajemy pytania naszym przyjaciółkom, mężczyźni tego nie robią.
[EX A]: （ 笑 ） ジェーン ： 女同士だとそんな質問をし合うけれど男性はしないわね
[EX Q]: Powszechnie obserwujemy to na blogach.
[EX A]: 様々なブログにも見られます
[EX Q]: Chciałbym, żeby to istniało wcześniej, gdy robiłem to po raz pierwszy. Jestem bardzo podekscytowany. Ponieważ projekt, który założyliśmy, posiada dane o lekach, które mogą działać. Chciałbym je pokazać.
[EX A]: | [
-0.9359944462776184,
0.22706595063209534,
-0.15416833758354187,
-0.7158787250518799,
0.08858303725719452,
-0.3200526833534241,
1.1046271324157715,
-0.07335841655731201,
0.7172476053237915,
-0.8018090724945068,
-0.6980677843093872,
0.5164857506752014,
-1.1486910581588745,
0.1025780960917472... |
Read the given query and classify it as a 'Good' or 'Bad' query depending on how well the query is formed, 'Bad' being the expected output for a not so well formed query and 'Good' being the expected output for a well formed query. A query may be wrong based on common sense or general facts, but if it is well formed, you should answer with Good.
[EX Q]: What is the height of mount Anconcagua ?
[EX A]: Good
[EX Q]: What is the instrament used mo measure lenght ?
[EX A]: Bad
[EX Q]: How many of Ohio 's electoral votes went to Romney in 2012 ?
[EX A]: | [
-0.8109906315803528,
0.4636509418487549,
-0.05510805547237396,
-0.05387434363365173,
-0.4489307403564453,
-0.8067154288291931,
0.07747000455856323,
0.8639154434204102,
0.142856627702713,
-0.025426585227251053,
-0.5556133389472961,
-0.00035887351259589195,
-0.6090012788772583,
-0.5166886448... |
In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.
[EX Q]: [1925, 1033, 'n', 1719, 1863, 9415, 'D', 8649, 's', 1653, 'V', 4263, 7099, 1825, 4487, 'G', 6067, 1553, 2517, '7743', '3161', 'X', '5815', '8019', '7445', 'H', 'g', '3451', '7313', 'j', 'v', '8927', '1115', 'b', 't', '1253', '8603', 'p', 'p', 'c', 'i', '8035', 'Z', 'Z', '3931', '4321', 'q', '2639', 'S', 'z', 8647, 9547, 'W', 7287, 7347, 'N', 'n', 'T', 5997, 4799, 'V', 'H', 4561, 'B', 2887, 9375, 3029, 'Y', 'x', 'J'], [6377, 'o', '7743', '3161', 'X', '5815', '8019', '7445', 'H', 'g', '3451', '7313', 'j', 'v', '8927', '1115', 'b', 't', '1253', '8603', 'p', 'p', 'c', 'i', '8035', 'Z', 'Z', '3931', '4321', 'q', '2639', 'S', 't', 'c', 7365, 3141, 5971, 6183, 'H', 3775, 'o', 2757, 9621, 'g', 'g', 1713, 'M', 9787, 5173, 9745, 'J', 'N', 8953, 'K', 1443, 'w', 8793, 9963, 6383, 3985, 9087]
[EX A]: 7743, 3161, X, 5815, 8019, 7445, H, g, 3451, 7313, j, v, 8927, 1115, b, t, 1253, 8603, p, p, c, i, 8035, Z, Z, 3931, 4321, q, 2639, S
[EX Q]: [7667, 5143, 'T', 'E', 'T', 'q', 'Q', 'i', 'c', 'A', 7503, '3605', 'c', 'c', '9759', '4535', '2651', 'M', 'f', 'm', '1859', '1089', '8417', '6247', 'B', '167', '2481', '5505', 'r', '7913', 'L', '9891', 'Z', '9983', 't', 'B'], ['M', 'S', 'J', 7313, 2291, 'e', 'T', 's', 'Q', 9505, 2219, 7845, 'K', 2339, 2553, 6137, 'j', 's', 6735, 7595, '3605', 'c', 'c', '9759', '4535', '2651', 'M', 'f', 'm', '1859', '1089', '8417', '6247', 'B', '167', '2481', '5505', 'r', '7913', 'L', '9891', 'Z', '9983', 'M', 'v', 'B', 8189, 4919, 9041, 4579, 'V']
[EX A]: 3605, c, c, 9759, 4535, 2651, M, f, m, 1859, 1089, 8417, 6247, B, 167, 2481, 5505, r, 7913, L, 9891, Z, 9983
[EX Q]: [4693, 'T', 3627, 8953, 5875, 4249, 9677, '923', '3023', '1001', '4869', 'R', '8209', 'a', 'Z', '1559', '347', '4085', 'H', 'N', 4883, 5269, 8481], [9079, 'i', 'B', 5451, 'Z', '923', '3023', '1001', '4869', 'R', '8209', 'a', 'Z', '1559', '347', '4085', 'n', 'H', 'y', 8583, 'h', 8483, 'f', 6927, 'T', 8563]
[EX A]: | [
-0.43638503551483154,
0.17017802596092224,
-0.3983142077922821,
-0.21252025663852692,
-0.30075162649154663,
-0.5336438417434692,
0.8472561836242676,
0.6797863245010376,
-0.617156982421875,
0.10179692506790161,
-0.8190960884094238,
0.34543463587760925,
-0.4108642637729645,
0.088414266705513... |
Classify the relation of question with context to one of these categories: 1) award received, 2) based on, collection, 3) conflict, 4) constellation, 5) convicted of, 6) date of death, 7) director, 8) drafted by, 9) educated at, 10) medical condition, 11) military branch, 12) narrative location, 13) occupation, 14) original network, 15) parent company, 16) point in time, 17) production company, 18) residence, 19) series, 20) service entry, 21) sex or gender, 22) spouse, 23) standards body question.
Q: Context : This has never been established as there are no witnesses to any verbal exchange and Susan Newell never pleaded guilty (first blaming her husband then citing insanity without giving details into the murder.)
Question : Which crime Susan Newell is considered to have commited?
A: | [
-0.17344963550567627,
0.9319791793823242,
0.27905508875846863,
-0.2751505970954895,
0.22044578194618225,
0.7939709424972534,
0.045057691633701324,
0.6295214295387268,
-0.09521936625242233,
0.28748422861099243,
0.07171069830656052,
0.2850964665412903,
-0.3533090651035309,
-0.377299696207046... |
In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write an implausible POS tag to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb
[Q]: What is the part-of-speech tag of the word "their" in the following question: Which athlete received their medal earlier ? Was it a Turkish boxer who won a silver medal in light-flyweight at the 2004 Olympics , or the person holding six European and one world record ?
[A]: DT
[Q]: What is the part-of-speech tag of the word "stadium" in the following question: What was the Gaelic name of the town housing the nicknamed 'Tony Macaroni ' stadium ?
[A]: WP
[Q]: What is the part-of-speech tag of the word "Who" in the following question: Who is the chairman of the club who 's last post-season series win was in the first series that the Nashville Predator qualified for ?
[A]: | [
0.4070587754249573,
0.6157684326171875,
-0.6473549604415894,
0.5721379518508911,
0.017516810446977615,
-0.42051947116851807,
0.8991411328315735,
0.6158725619316101,
-0.28199902176856995,
-0.02496298775076866,
-1.0850074291229248,
0.6946721076965332,
-0.734898567199707,
-0.07397674769163132... |
You will be given a definition of a task first, then some input of the task.
You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Spanish.
9 ・ 11の後その持論は覆されました
Output: | [
0.015162890776991844,
0.5280101895332336,
0.372055321931839,
-0.7713485956192017,
-0.1958458423614502,
-0.3975934386253357,
0.1731185019016266,
0.7921594977378845,
0.09442809224128723,
-0.5963120460510254,
-0.2975847125053406,
-0.404760479927063,
-0.8478484153747559,
-0.0005832522292621434... |
In this task you will break down a question into the basic steps required to answer it.
A question decomposition is a numbered list of operations that must be performed to answer the original question. Imagine explaining your question to a friendly droid by listing each action it should take in order for the question to be answered. Each step in our decomposition should refer to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.)
Here are the list of step templates and their description:
Select: A select step is used to return a set of objects. There are no references to previous steps in a select step. template: Return [attributes]
Filter: A filter step is used to return results from a previous step to which a certain condition applies. template: Return [#step] [condition]
Project: A project step should return certain attributes of the results of a previous step. template: Return [attributes] of [#step]
Aggregate: An aggregate step returns an aggregator function applied on a step's result. template: Return the [aggregator] of [#step].
Group: A group step is an aggregator applied on attributes. template: Return the [aggregator] of [#step] for each [attribute]
Superlative: A superlative step is used to return the result with a highest/lowest attribute among other results. template: Return [#step1] [where] [#step2] [is] [highest / lowest]
Comparative: A comparative step is used when we need to compare an attribute with a number to filter results. template: Return [#step1] [where] [#step2] [comparator] [number]
Union: A union step is used to return results of two steps together. template: Return [#step1] [or / ,] [#step2]
Intersection: An intersection step returns the result that two steps have in common. template: Return [attribute] of both [#step1] and [#step2]
Discard: A discard step returns result of a step and excludes result of another step from it. template: Return [#step1] besides [#step2]
Sort: A sort returns result of another step in a specific order. template: Return [#step1] [ordered / sorted by] [#step2]
Is true: An is true step checks a condition on another result and returns a true or false. template: Return [is / if] [condition]
Arithmetic: An arithmatic step operates an arithmatic operation on one or more steps. template: Return the [arithmetic op.] of [#step1] [and] [#step2].
One example: question: What are the distinct creation years of the departments managed by a secretary born in state 'Alabama'?
Solution is here: #1 return secretaries
#2 return #1 born in state 'Alabama
#3 return departments managed by #2
#4 return distinct creation years of #3
Explanation: Referring to previous steps is vital in constructing multi-step decompositions. In this example each step refers to the step before to perform a single filter on it to reach the final result.
Now, solve this: question: what is the earliest flight departing san francisco and arriving in boston on november ninth
Solution: | [
1.189985752105713,
-0.012529823929071426,
-0.5251471400260925,
0.4414918124675751,
0.19486361742019653,
-0.3261980414390564,
1.2066879272460938,
0.16166338324546814,
-0.45272403955459595,
0.42805176973342896,
-0.45172837376594543,
0.29167670011520386,
-0.09983660280704498,
0.62999153137207... |
Detailed Instructions: In this task, you are given a text from tweets and a boolean question whether this tweet has positive sentiment or negative sentiment. Your task is to generate answer "yes" when the tweet has that particular sentiment, otherwise generate answer "no".
Q: Tweet: Brasil 4 x 0 Uruguai : So good to win! Question: is it a positive tweet?
A: | [
-0.9731731414794922,
0.44305676221847534,
-0.13055233657360077,
0.41281625628471375,
-0.5313664078712463,
-0.7616435289382935,
-0.1909209042787552,
0.7407267093658447,
0.4313965439796448,
0.1141631081700325,
-0.7581919431686401,
0.055900685489177704,
0.23158931732177734,
-0.202505931258201... |
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, ['5541', '6973', '6789', 'k', '4093', '5053', '1061', 'S', 'U']
Solution: | [
-0.15655732154846191,
0.8164072036743164,
-0.3896770477294922,
-0.8173683881759644,
-0.3229601979255676,
-0.09997089207172394,
0.9725753664970398,
0.053596124053001404,
-0.0902608335018158,
-0.08251083642244339,
-0.4631942808628082,
0.11334498226642609,
0.021949652582406998,
-0.18336507678... |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
In this task, you will be presented with an English sentence, and you have to translate it into Arabic.
But if the shares belong to Geoffrey Charles, well, then George cannot touch them.
Solution: لكن لو كانت الأسهم بإسم جوفري تشارلز لن يمكن لجورج المساس بهم.
Why? This is a good example. The above sentence is correctly translated from English to Arabic.
New input: In the Security Council's recent review of the report of the Secretary-General on the prevention of armed conflict, the Chinese delegation, in its analysis of the causes of armed conflict, made clear its views on ethnic conflicts and religious disputes in some countries and regions, and it emphasized the importance of promoting the democratization of State-to-State relations and strictly following the basic norms guiding such relations.
Solution: | [
0.19637052714824677,
0.1877712607383728,
-0.05634746700525284,
-1.1379897594451904,
0.2174845039844513,
-0.09237276762723923,
0.8923882246017456,
0.09240937232971191,
0.2130090296268463,
-0.13258109986782074,
0.29884517192840576,
0.46840304136276245,
-0.3799760639667511,
-0.132435098290443... |
Definition: You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Arabic.
Input: その共生関係は時に素晴らしい適応を生みますこれはスズメガの一種で美しい適応をしています
Output: | [
-0.35096240043640137,
0.2661950886249542,
-0.5277508497238159,
-0.5092761516571045,
-0.19425900280475616,
-0.11556773632764816,
0.5134201049804688,
-0.1284342110157013,
0.3426939845085144,
0.15732842683792114,
-0.7529134750366211,
0.20980945229530334,
-0.5942454934120178,
0.379604697227478... |
You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label "Yes", otherwise label "No". Do not use any facts other than those provided in the sentence while labeling "Yes" or "No". There are only two types of valid responses: Yes and No.
One example is below.
Q: Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?
A: Yes.
Rationale: The sentence says that "the Democrats" have to be appeased, which answers the question. So, the correct label should be "Yes".
Q: Sentence: Jacob also had a cool RC car that William liked to play with.
Question: What was at Jacob's house that William liked to play with?
A: | [
-1.1038607358932495,
0.17671924829483032,
0.4986211359500885,
0.42704886198043823,
-0.6411193013191223,
-1.4201031923294067,
0.38030925393104553,
0.6379566192626953,
0.2457110732793808,
0.22875407338142395,
-0.04585203528404236,
-0.01771767996251583,
-0.06916221976280212,
0.085971444845199... |
Instructions: Given a post that is a real-life anecdote of a complex ethical situation and a question asks if AUTHOR, NOBODY, EVERYBODY, or OTHER is wrong in the situation. Answer the question and classify your answers into yes or no.
Input: Is OTHER wrong in the post ? POST : My GF (20F) and I (22M) have been together for about 3 years. We have been playing the long distance game for about a year now, as she moved about 3 hours drive to the city to be with her family, while I stayed due mainly to work as well as my family being here.
At the moment she is searching for work after being made redundant, but has been unemployed for nearly 2 months now. I have been working full time, as well as working a 2nd job part time a few nights a week to get ahead on my finances. My life at the moment is basically stretched between work and sport, while hers has been netflix and helping around the house while her family work. However I have been trying my best to visit, and over the last few months have been visiting fortnightly to every 3 weeks or so, while due to her financial situation she's only come down a couple times, one of which was she hitched a ride with a family member who was coming down to visit some family friends, but only stayed the night. I understand her lack of visits due to her finances, but I have offered quite a few times to pay for fuel so she can come and visit, which she declines because she doesn't want to take my money.
She is coming back to my town for 3 weeks to be paid to housesit for a family friend of hers, which is only feasible due to her lack of work. We will ideally be spending a fair bit of time together while she is in town, but she is only coming for the housesitting job, she wouldn't of come otherwise.
The last time I went to visit was 2 weekends ago, when I was in the city for a work function, which she was my +1 for. I haven't visited since as I knew she was coming to my town anyway, and I plan to make the most of having her around so I thought I would use the weekends before to get stuff done. I have a big family holiday coming up in the start of May, and so am preparing for that, while also trying to actually take time out on my weekends to play sport, help out around the house (recently helped my dad with a paving job at home) and just bum around, stuff I can't do when I'm visiting my GF. It's a bitch driving 3 hours there and 3 back, and is generally quite an expensive weekend factoring in fuel, meals and entertainment.
Last night we had an argument about how over the 2 month period between March and April I will only spend 1 weekend at hers, while she is going to be spending 3 weeks in my town. I told her that's a bit unfair as she will be coming down so I don't have a reason to drive to her house, but she told me that she just doesn't think I visit enough. I told her she needs to understand I have a life outside of our relationship, and that due to her work situation she is able to get things done during the week, while anything I want to do outside of work is generally reserved for weekends because I simply don't have the time. She just replied with "whatever, night" and ended our phone call.
Reddit, AITA for not visitng?
Output: | [
-0.09110553562641144,
0.245548278093338,
-0.05731625109910965,
-0.03606090322136879,
0.5167088508605957,
-0.5562469959259033,
0.34632736444473267,
0.7972918748855591,
-0.25794482231140137,
-0.3963750898838043,
-0.04344779998064041,
0.2189275175333023,
-0.41575703024864197,
-0.1879849135875... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.