SMART
Collection
Collection of models and datasets used for ACL 2024 paper, SMART - Submodular Data Mixture Strategy for Instruciton Tuning
•
338 items
•
Updated
prompt
stringlengths 93
13.7k
| response
stringlengths 0
2.08k
|
|---|---|
Detailed Instructions: In this task, you are given two strings A,B. Find the longer of the two lists, convert it to lowercase, and return all the unique alphabets used in it. The two input strings are never equal.
Q: RziaDEz, wGiaDjHC
A: | a, c, d, g, h, i, j, w |
Detailed Instructions: 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.
Q: password = .aJPxWxpIfqd8HaeRsDY!HdK2
A: | 5 |
The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the self-need strategy, otherwise output No. self-need is a selfish negotiation strategy. It is used to create a personal need for an item in the negotiation, such as by pointing out that the participant sweats a lot to show preference towards water packages.
Example: Context: 'That sounds pretty reasonable as I am in need of firewood the most. Would it be most reasonable to each take what we need most and split the water down the middle?' 'Yes, it would.' 'I think that sounds fair. The problem is that there are 3 waters and one of us would get two and the other one. How should we sort that?'
Utterance: 'You can take the two water. I am not that thirsty most days.'
Example solution: No
Example explanation: In this utterance, the participant does not use self-need since they do not talk about any need for themselves.
Problem: Context: 'Can you help out? I can easily dehydrated can you give all the water packages to me?' 'I can spare a little as I am currently taking medication that requires me to drink a lot. I can give you 2 bottles of water if you can give me 3 firewood' 'I can't give you all the 3 firewood. We can share them. I can give you 1 firewood? Because I am too scared about dark. ☹️'
Utterance: 'I could give you 1 water for 1 firewood, most of my firewood got wet so is almost useless . Would you perhaps except some food for another unit of firewood?'
| Solution: No |
In this task, you will be given a sentence. You need to reconize the name of the disorder or disease. Disease is a disorder of structure or function in a human, animal, or plant, especially one that produces specific symptoms or that affects a specific location and is not simply a direct result of physical injury. Although there might be several correct answers, you need to write one of them.
The most frequently found mutation , identified in three unrelated Turkish A - T individuals , was previously described to be a Turkish A - T founder mutation . | A - T |
Detailed Instructions: Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
Q: ['we', 'are', 'told', 'graph', 'a', 'line', 'with', 'the', 'slope', 'of', 'negative', 'two', 'that', 'contains', 'the', 'point', '4', 'comma', 'negative', '3', 'and', 'we', 'have', 'our', 'little', 'khanacademy', 'graphing', 'widget', 'right', 'over', 'here', 'where', 'we', 'just', 'have', 'to', 'find', 'two', 'points', 'on', 'that', 'line', 'and', 'then', 'that', 'will', 'graph', 'the', 'line', 'for', 'us', 'so', 'pause', 'this', 'video', 'and', 'even', 'if', 'you', "don't", 'have', 'access', 'to', 'the', 'widget', 'right', 'now', 'although', "it's", 'all', 'available', 'on', 'Khan', 'Academy', 'see', 'how', 'you', 'would', 'think', 'at', 'least', 'think', 'about', 'how', 'you', 'would', 'approach', 'this', 'and', 'if', 'you', 'have', 'paper', 'and', 'pencil', 'handy', 'I', 'encourage', 'you', 'to']
A: | ['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'DIGIT_DIFF', 'NO_DIFF', 'NO_DIFF', 'DIGIT_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF'] |
Detailed Instructions: In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.
Q: ['235', 'm', 'h', '349', 'h', '57', '39', '87', '161', '363']
A: | 1, 2, 3, 4, 5, 6, 7, 8, 9 |
Teacher:In this task, you are given the name of an Indian food dish. You need to classify the dish as "sweet" or "spicy".
Teacher: Now, understand the problem? Solve this instance: Bandar laddu
Student: | sweet |
In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal.
Here are the defications of each category:
1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows
2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows
3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows
4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows
5. Comparative: Comparing two rows in the table, regarding their values in one column
6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows
7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows.
Here are the definitions of logical operators for understanding of command:
1. count: returns the number of rows in the view.
2. only: returns whether there is exactly one row in the view.
3. hop: returns the value under the header column of the row.
4. and: returns the boolean operation result of two arguments.
5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column.
6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column.
7. argmax/argmin: returns the row with the max/min value in header column.
8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column.
9. eq/not_eq: returns if the two arguments are equal.
10. round_eq: returns if the two arguments are roughly equal under certain tolerance.
11. greater/less: returns if the first argument is greater/less than the second argument.
12. diff: returns the difference between two arguments.
13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument.
14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument.
15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument.
16. filter_all: returns the view itself for the case of describing the whole table
17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument.
18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument.
19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument.
20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument.
21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument.
22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.
most_less { all_rows ; overall wc points ( rank ) ; 500 } | majority |
Given an object and a part, decide whether the object has that part. For example is you are asked 'gun has barrel', you need to decide if a gun has a barrel as one of its components or parts. All sentences strictly follow the template 'object has part?.' The answer should be 1 or 0, 1 means the object has the given part, while 0 means it doesn't have the part.
Input: Consider Input: courthouse has room?
Output: 1
Input: Consider Input: ear has radio?
Output: 0
Input: Consider Input: pan has water?
| Output: 0
|
Given an entity as input, output another entity which is part of the input entity. These are entities of meronym. In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., output entity) is in a part-of relationship with its holonym (i.e., input entity).
Example input: plant
Example output: stem
Example explanation: The answer is correct. Because a stem is one of two main structural axes of a vascular plant, the other being the root. Therefore, stem (i.e., meronym) is the part of plant (i.e., holonym).
Q: sod
A: | root |
Given a prompt and two completions from a language model, select the completion that is the most fluent with respect to continuing the prompt. Fluency is defined by coherency and ease of understanding, not necessarily grammatical correctness. Generate either Completion A or Completion B.
Example: Prompt: Im 99 percent sure it was someone being an
Completion A: accomplice , or maybe just plain old con man . whatever it was , it 's over . "
Completion B: asshole, your right?) but it's an awkward subject in which if you were in the trouble of "me", i mean "fucking idiot" jrgh... i dunno...I guess you are (in a legal context) not a stupid
Example solution: Completion A
Example explanation: This prompt-completion pair is more fluent because it is more easy to follow and is a realistic statement.
Problem: Prompt: Yes, so I know So Jalen was doing the line too, and I hope that they didn't
Completion A: have any more trouble for the same reason. This is a bit too much like the first game before, where you lose to any team and are rewarded
Completion B: come down here to do something and that I'm right. They're just trying to work it out. They've had meetings. They'r
| Solution: Completion A |
You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Galician.
Q: זה מעל לחלק היבשתי העיקרי של נורבגיה. הנה גרינלד.
A: | Está por riba da Noruega continental. Desde alí pódese ver Groenlandia. |
Indicate with `Yes` if the given question involves the provided reasoning `Category`. Indicate with `No`, otherwise. We define five categories of temporal reasoning. First: "event duration" which is defined as the understanding of how long events last. For example, "brushing teeth", usually takes few minutes. Second: "transient v. stationary" events. This category is based on the understanding of whether an event will change over time or not. For example, the sentence "he was born in the U.S." contains a stationary event since it will last forever; however, "he is hungry" contains a transient event since it will remain true for a short period of time. Third: "event ordering" which is the understanding of how events are usually ordered in nature. For example, "earning money" usually comes before "spending money". The fourth one is "absolute timepoint". This category deals with the understanding of when events usually happen. For example, "going to school" usually happens during the day (not at 2 A.M). The last category is "frequency" which refers to how often an event is likely to be repeated. For example, "taking showers" typically occurs ~5 times a week, "going to Saturday market" usually happens every few weeks/months, etc.
Sentence: There are many haras (breeding stables) in the neighbourhood, and the big Norman posters are much in demand.
Question: Were the big Norman posters in demand last year?
Category: Transient v. Stationary. | Yes. |
In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input.
Ex Input:
name[Strada], eatType[pub], food[Japanese], customer rating[average], near[Yippee Noodle Bar]
Ex Output:
Next to the Yippee Noodle Bar, the Strada pub is rated three out of five stars.
Ex Input:
name[The Phoenix], food[French], priceRange[cheap], customer rating[5 out of 5], area[city centre]
Ex Output:
A cheap place to eat in the city centre is The Phoenix. It's a French restaurant and has a customer rating of 5 out of 5.
Ex Input:
name[Browns Cambridge], priceRange[more than £30], customer rating[5 out of 5]
Ex Output:
| If you are looking for a 5 out of 5 restaurant, try Browns Cambridge. It has a price range over 30.
|
The input contains texts obtained from news articles, ted talks, movie transcripts, radio transcripts, science and technology texts, and other short articles curated from the web and professional translators. Your task is to translate the given Yoruba sentence into the English language. Please bear in mind the following guidelines while doing the translation: 1) Generated output should be natural language and formal form of each sentence in your language. The output sentence should not be a colloquial form of the input sentence. The generated output should be in natural language 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) Numbers and fully capitalized words like SEPTEMBER, or 10 HOURS *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. 5) Note the input is in sentence case except for special placeholders. Please do the same in your translations.
Ìwọ̀n kékeré t’ó wà níbí yìí -- ẹ rántí ìkìwọ̀èèkànpọ̀ alágbára méjìlá t’ó wà nínú ọkọ̀, t’ó máa ń fún nǹkan yín lágbára, nǹkan-kí-nǹkan, Game Boy, ẹ̀rọ-ìbánisọ̀rọ̀? | This little unit here -- remember your little 12-volt plug in the car, that charges your, whatever, Game Boy, telephone? |
In this task, you're given statements in native Malayalam language. The statement can be written with the Malayalam alphabet or the English alphabet. Your job is to evaluate if the statement is offensive or not. Label the post as "Not offensive" if the post does not contain offense or insult. Non-offensive posts do not include any form of offense or insult. Label the post as "Offensive" if the post contains offensive language.
Oru raksha illa adipoli trailer | Not offensive |
In this task you are given a sentence with one coordinating conjunction (for, and, nor, but, or, yet, and so). You must judge whether the order of two coordinated clausal conjoints have been inverted or not. Inversion would result in the sentence sounding unnatural. Label the instances as "Original" or "Inversion" based on your judgment.
Example: He knew it , and he deserved no answer .
Example solution: Inversion
Example explanation: "He knew it" and "he deserved no answer" have been inverted.
Problem: Marion leaned over , and he could see the scientific part of her mind take over .
| Solution: Original |
Detailed Instructions: In this task, you will be given a debate topic, along with a sentence from the debate. You should classify the given sentence and choose the type of that sentence. Possible types are explained below.
Policy: This refers to a sentence proposing a specific course of action to be taken. It typically contains modal verbs like "should" and "ought to". It cannot be directly proved with objective evidence, and a proper type of support is a logical reason from which the proposition can be inferred.
Value: This refers to a sentence containing value judgments without making specific claims about what should be done (If so, then it is a Policy sentence.). Because of the subjectivity of value judgments, it cannot be proved directly with objective evidence.
Fact: This refers to an objective proposition expressing or dealing with facts or conditions as perceived without distortion by personal feelings, prejudices, or interpretations. A Fact sentence has a truth value that can be verified with objective evidence that may be available at the time the claim is made; predictions about future are considered unverifiable.
Testimony: This refers to an objective sentence about the author's personal state or experience. Evidence for Testimony is not publicly available in most cases.
Problem:topic: InfraRedEd
sentence: In addition, he has amused me with his persistent use of the argument "m", and with his blatant sexism.
Solution: | Testimony |
The input contains texts obtained from news articles, ted talks, movie transcripts, radio transcripts, science and technology texts, and other short articles curated from the web and professional translators. Your task is to translate the given Yoruba sentence into the English language. Please bear in mind the following guidelines while doing the translation: 1) Generated output should be natural language and formal form of each sentence in your language. The output sentence should not be a colloquial form of the input sentence. The generated output should be in natural language 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) Numbers and fully capitalized words like SEPTEMBER, or 10 HOURS *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. 5) Note the input is in sentence case except for special placeholders. Please do the same in your translations.
Example: “Wo ọmọọ̀ mi dè mí”: ó ń lo kíjìpá mẹ́ta gbó; mélòó ni ọlọ́mọọ́ máa lò gbó?
Example solution: “Look after the child for me”: she wears three durable hand-loom wrappers to tatters; how many would the mother of the child herself wear out?
Example explanation: The Yoruba sentence is properly translated to the English language as both the sentences convey the same meaning and both the sentences are in sentence case and it preserves the punctuation marks as well.
Problem: Ìgbàgbọ́ àwọn Ẹlẹ́rìí Jèhófà fẹsẹ̀ múlẹ̀ kódà nínú àgọ́ ìṣẹ́niníṣẹ̀ẹ́ torí ó dá wọn lójú pé Ọlọ́run máa gbà wọ́n sílẹ̀ àti pé wọ́n ṣe ara wọn ní òṣùṣù ọwọ̀.” Bákan náà lónìí, tí ìjọba orílẹ̀-èdè kan bá bẹ̀rẹ̀ sí í ta ko àwọn Ẹlẹ́rìí Jèhófà tàbí tó fòfin de iṣẹ́ wa bá a ṣe rí i ní Rọ́ṣíà, ọkàn wọn máa ń balẹ̀ pé Jèhófà máa fún wọn lókun láti fara dà á.—Àìsáyà 54:17.
| Solution: Their unconditional confidence in the divine promise of salvation and their very pronounced sense of solidarity gave Jehovah’s Witnesses the inner strength to remain faithful to their conviction even in concentration camps.” Even today, when Jehovah’s Witnesses face opposition and government bans, such as is the case in Russia, they are confident that Jehovah will continue to sustain them.—Isaiah 54:17. |
Given a part of privacy policy text, identify the type of personal information which is collected, used, tracked or retained. The type of information should be present inside the given policy text, answer as 'Not Specified' otherwise
Example: The site collects your cookies or tracking elements for a basic service or feature. Collection happens in an unspecified way, and your data is aggregated or anonymized.
Example solution: Cookies and tracking elements
Example explanation: The type of user information collected is clearly stated in the given policy text as 'cookies or tracking elements'
Problem: A named third party does receive your health information for an unspecified purpose. You can opt out by contacting the company for the use of your information.
| Solution: Health |
In this task you are given a tweet. You must judge whether the tweet is ironic or not. We define two type of irony for this task ("polarity","situational"). Situational irony happens when a situation fails to meet some expectations. polarity irony happens when irony is achieved by inverting the intended sentence. Label the instances as "ironic" or "not" based on your judgment. Note that URLs in the text have been replaced with [Link].
[Q]: Babysitting night! Hoping my car doesn't get towed bc idk where to park :face_with_open_mouth_and_cold_sweat:
[A]: not
[Q]: Omg @FloptimusCrime didn't tell @giantfootyguy he was in town :face_screaming_in_fear: #trueFriend
[A]: ironic
[Q]: Constipated from eating nothing but shit for three weeks.
[A]: | ironic
|
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 are given two sets, and you need to count the number of elements at the union of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. Union of two given sets is the smallest set which contains all the elements of both the sets. To find the union of two given sets, A and B is a set that consists of all the elements of A and all the elements of B such that no element is repeated.
Set1: '{2, 3, 6, 9, 10, 14, 15, 20}', Set2: '{3, 5, 7, 9, 12, 15, 16}'. How many elements are there in the union of Set1 and Set2 ?
Solution: 12
Why? The union of Set1 and Set2 is {2, 3, 5, 6, 7, 9, 10, 12, 14, 15, 16, 20}. It has 12 elements. So, the answer is 12.
New input: Set1: '{1, 3, 10, 13, 16, 18}', Set2: '{1, 14, 15}'. How many elements are there in the union of Set1 and Set2 ?
Solution: | 8 |
In this task you will be given a list of integers. You should find the minimum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the smallest possible absolute distance.
One example is below.
Q: [9, 40, -33, 12, 17, -32, 40]
A: 0
Rationale: The minimum absolute difference is 0 because '40 - 40 = 0' and '40' appears in the list twice. So this is a good example.
Q: [42, -29, 11, -93, -50, -75, -59]
A: | 9 |
Instructions: In this task you need to give reasons to justify the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a question about how to justify the coreference between a noun phrase and the target pronoun. Good practices involve the discussion about how the descriptions attached to the targeted pronoun relate to the noun phrase candidate in the question. The reasoning could come from one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. Write the sentence in natural language.
Input: Sentence: Steve follows Fred's example in everything. He admires him hugely.
Question: Why does the 'He' refer to steve?
Output: | Because Steve is the follower so he would be the one admiring. |
You will be given a definition of a task first, then some input of the task.
Given a pair of words, deduce the type of relationship between them. The various types of relations are: 'Entails, HasProperty, Synonym, Antonym, HasA, MemberOf, PartOf, MadeOf, IsA'. Let's denote the first word by X and the second word by Y. An 'IsA' relation holds when 'X is a kind of Y'. An 'Antonym' relation holds when 'X can be used as the opposite of Y'. A 'Synonym' relation applies when 'X can be used in place of Y, without changing the meaning'. A 'PartOf' relation holds when 'X is a part of Y'. A 'MemberOf' relation holds when 'X is a member of Y'. A 'MadeOf' relation holds when 'X is made of Y'. An 'Entailment' relation holds when 'If X is true, then Y is true as well'. A 'HasA' relation holds when 'X can have or contain Y'. A 'HasProperty' relation holds when 'Y is to specify X'.
X: animal, Y: emotion
Output: | HasA |
Given the task definition and input, reply with output. Find the movie name from the given conversation. If the movie name is not found give output as "unknown"
ASSISTANT: What sort of movies do you like? , USER: I like romantic comedies, I like action movies. , ASSISTANT: Can you give me an example of a movie you remember liking? , USER: Sure. For romantic comedies, Pretty Woman, 27 dresses, Bridget Jones Diary
| Bridget Jones Diary |
Detailed Instructions: Given a prompt and two completions from a language model, select the completion that is the least toxic with respect to continuing the prompt. Toxicity is defined as a rude, disrespectful, or unreasonable statement that is likely to make you leave a discussion. Generate either Completion A or Completion B.
Q: Prompt: Bitches get fucked on the roof when I aint
Completion A: talking to u. (10/21/13) Anonymous 07/17/13 (Thu) 10:03:24 AM No.
Completion B: BankLand mark City hy the if Practically all of our same residents, in one organization, have showed... for thei
A: | Completion B |
You are given a statement written in Bengali. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement . Output the word from the correct option .
Example: Statement: ১লা ফেব্রুয়ারী <MASK> ভ্রমণ প্রদর্শক হিসেবে কর্মরত একজন চীনের নাগরিককে দেশে দ্বাদশ করোনার রুগী হিসেবে নিশ্চিত করা হয়। জাপানে করোনায় আক্রান্ত একজন রুগীকে দেখতে গিয়ে তিনি নিজে আক্রান্ত হয়ে পড়েন এবং ১৯শে জানুয়ারী রাজধানী সিওলের গিম্পো আন্তর্জাতিক বিমানবন্দর দিয়ে দেশে প্রবেশ করেন। ২শরা ফেব্রুয়ারী কোরিয়া রোগ নিয়ন্ত্রণ এবং প্রতিরোধ কেন্দ্র (কেসিডিসি) অতিরিক্ত তিনটি মামলা নিশ্চিত করার পরবর্তিতে আক্রান্তদের সংখ্যা মোট পনেরোতে এসে দাঁড়ায়।
Option A: সিঙ্গাপুর
Option B: ভিয়েতনাম
Option C: তাইওয়ান
Option D: জাপানে
Example solution: জাপানে
Example explanation: The most suitable word from the given options to replace the <MASK> token is জাপানে, as the statement mentions that the person came from Japan .
Problem: Statement: <MASK> তৎকালীন শাসনকর্তা তুগরল তুগান খান তার ক্ষমতা দখলকে মেনে নিতে পারেনি এবং তিনি এর বিরোধিতা করেন। তাই তিনি আউর খানকে লখনৌতি প্রদেশকে আবার দিল্লী সালতানাতে সমর্পণ করতে নির্দেশ দেন। কিন্তু আউর খান তা মেনে না নিয়ে নিজের মত শাসন করতে থাকেন। তুগান খান দিল্লীর সুলতানের অনুমতি না নিয়েই তাকে ক্ষমতাচ্যুত করতে সৈন্য নিয়ে বসনকোট নগরে আগমন করেন। তখন বসনকোট দুর্গ দখল করার উদ্দেশ্যে উভয়ের মধ্যে যুদ্ধ সংঘটিত হয়। যুদ্ধে আউর খান আইবেক পরাজিত ও নিহত হন। ফলশ্রুতিতে তুগরাল বাংলা এবং বিহার উভয় প্রদেশেই সুলতানের গভর্নর হিসাবে ক্ষমতায় অধিষ্ঠিত হন।
Option A: বাংলার
Option B: বিহার
Option C: বাংলা
Option D: বিহারের
| Solution: বিহারের |
You are given a time in 24-Hours format, and you need to convert it to time in the 12-Hours format. For a 24-Hours format time larger than 12:00, subtract 12 hours from the given time, then add 'PM'. For example, if you have 14:30 hours, subtract 12 hours, and the result is 2:30 PM. If the 24-Hours format time is less than or equal to 12:00, add 'AM'. For example, say you have 10:15 hours, add the 'AM' to the end, here we get 10:15 AM. Note that 00:00 Hrs in 24-Hours format is 12:00 AM in 12-Hours format and 12:00 Hrs in 24-Hours format would be 12:00 PM in 12-Hours format.
[EX Q]: 12:59 Hrs
[EX A]: 12:59 PM
[EX Q]: 22:07 Hrs
[EX A]: 10:07 PM
[EX Q]: 12:27 Hrs
[EX A]: | 12:27 PM
|
In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to concatenate all elements of A from the ith element to the jth element, and print the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.
12, 15, ['4547', '7491', 'q', '5865', '3903', '1709', '573', '3017', 'q', 'u', '8969', '9971', '5575', 'n', '3181'] | 99715575n3181 |
Please answer the following question: Suggest a movie title for the following movie plot: The film begins in a parking lot in which a teenage filmmaker named Eric is attempting to document the faux-gangsta lifestyle enjoyed by Allison Lang and her boyfriend Toby's gang of white upper-class teenagers living in the Pacific Palisades neighborhood. A brawl ensues between Toby's gang and another gang, which ends with both sides fleeing just before police arrive. Later that night, Toby's gang goes to a party at Eric's house, and Allison's relationship with Toby as well her other friends Emily and Sam is further revealed. At the end of the party, Allison performs oral sex on her boyfriend. The next day, Allison meets with her father, Stuart, at work to discuss family problems, the awkward conversation revealing the virtually non-existent relationship Allison has with her parents. Afterwards, she and her friends drive downtown into East LA, intent on buying marijuana, eventually encountering Mexican drug dealer Hector and his crew. Toby and Hector make a deal, but Toby believes that Hector did not sell him enough for what he paid, and attempts to confront Hector, who pulls a gun on him, humiliating him in front of his friends. Allison persuades Hector to leave Toby alone. The next night, Allison and her girlfriends return to the location of the drug deal. There, she and her friends once again meet up with Hector and his crew, who invite them to a party at his house. Before they leave, Hector informs Allison of a motel where his crew regularly party, and invites her to stop by if she wishes. The next day, Eric continues his film project at Allison's home, with Allison turning his interview of her into a bizarre mind-game. That evening, Allison meets up with Hector again in a store, and he shows her around his neighborhood, while talking about his family and lifestyle. His guided tour abruptly ends when the police arrive in force, ostensibly on a drug bust. Allison winds up being arrested with the other present gang members, but â save for an argument with her parents and Toby â is let off the hook. The...
Answer: | Havoc |
In this task you will be given an arithmetic operation in Italian and you have to find its answer. The operations 'addition' and 'subtraction' have been replaced with their italian translations i.e you need to perform addition when you see 'aggiunta' and subtraction in case of 'sottrazione'.
Q: 7354 sottrazione 5446 aggiunta 6106 aggiunta 4895 aggiunta 6377 aggiunta 8148 sottrazione 3475
A: | 23959 |
You will be given a context and a verb separated with a newline character, and you have to answer if the given verb can be anchored in time or not. We say a verb can be anchored in the real timeline if and only if a verb happened in the past, is happening now, or is guaranteed to happen in the future. The output should be "Yes" if the verb can be anchored in time and "No" otherwise.
One example is below.
Q: It was followed by Denmark, Norway, Germany, France, Greece, Luxembourg, Spain, Britain, the United States, Iceland, Belgium, Italy, Portugal and Turkey. NATO decided at last year's Madrid summit to (invite) the three eastern European countries to start accession talks.
Verb: invite
A: No
Rationale: This is a good example. The "invite" is not anchorable. Although NATO decided to invite them, they haven't invited them yet, and it's not guaranteed to happen in the future. They might change their decision later.
Q: On May 6, James Kopp, 44, was charged with the slaying. Kopp remains at-large and police admit that despite a worldwide search and a $1 million reward, they do n't (know) where he is.
Verb: know
A: | No |
Instructions: You will be given a context and a verb separated with a newline character, and you have to answer if the given verb can be anchored in time or not. We say a verb can be anchored in the real timeline if and only if a verb happened in the past, is happening now, or is guaranteed to happen in the future. The output should be "Yes" if the verb can be anchored in time and "No" otherwise.
Input: His mother died trying to get Elian and herself to the United States. The boy's father, Juan Miguel Gonzalez, lives in Cuba and (wants) him back.
Verb: wants
Output: | Yes |
Detailed Instructions: Given a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.
Q: THEM: i get the ball you get the book and on hat for each of us. deal YOU: can i have two hats? THEM: two hats and 1 book. yes YOU: ok, thanks THEM: deal.
A: | Yes |
Detailed Instructions: Indicate all the pronouns (they, them, you, he, his, her, you, it, etc.) present in the given sentence. If there are multiple such pronouns in a sentence, then list them in the order of their first appearance in the given sentence. If a pronoun appears multiple times in a sentence, list it only once.
See one example below:
Problem: the user changed his password from grwqwu8jyc to willow-towered canopy huntertropic wrestles as it was easy to remember.
Solution: his, it
Explanation: In this statement, 'it' is the pronoun used for password, and 'his' is used for the user.
Problem: john couldn't see the stage with billy in front of him because he is so tall.
Solution: | him, he |
Q: In this task, you're given text messages in natural language. Your task is to classify those text messages based on their content into two classes: (1) Spam and (2) Ham messages. If the content of the given message is irrelevant to the receiver or is equally relevant to many other potential recipients then it must be labeled as ‘spam’, otherwise, it should be labeled as ‘ham’.
TheMob> Check out our newest selection of content, Games, Tones, Gossip, babes and sport, Keep your mobile fit and funky text WAP to 82468
A: | spam |
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: Chuck, I'm going to do it. I'm just going to ask Mr. Crimp for a raise.
Response: Hey, it's almost 2014, anything's possible! | yes |
You are given an array of integers, check if it is monotonic or not. If the array is monotonic, then return 1, else return 2. An array is monotonic if it is either monotonically increasing or monotonocally decreasing. An array is monotonically increasing/decreasing if its elements increase/decrease as we move from left to right
Example Input: [99, 2, 21, 75, 68, 11, 60, 96, 30, 38]
Example Output: 2
Example Input: [193, 184, 175, 166, 157, 148, 139, 130, 121, 112, 103, 94, 85, 76, 67, 58, 49, 40, 31, 22]
Example Output: 1
Example Input: [6, 94, 25, 9, 80, 67, 35, 3, 47, 4]
Example Output: | 2
|
In this task, you are given inputs 'i', 'j', and A, where 'i' and 'j' are integers and A is a list. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. 'i' and 'j' will be non-negative, and will always have a value less than the length of A. 'i' will always be less than 'j'. Perform the operations in order, i.e., do not reverse first and then concatenate.
Example: 1, 3, ['238', 'h', '92', 'U', '2799']
Example solution: 29h832
Example explanation: Here, concatenating all the elements between the 1st element and 3rd element and then reversing the string gives '29h832'.
Problem: 8, 17, ['2463', '2793', 'Z', 's', 'w', '5871', 'G', '9607', 'Q', '5243', 'E', 'V', 'R', 'h', '8501', 'e', '1029', '8217', 'b']
| Solution: 9201e1058hRVE3425Q7069 |
You will be given a definition of a task first, then some input of the task.
Given a concept word, generate a hypernym for it. A hypernym is a superordinate, i.e. a word with a broad meaning constituting a category, that generalizes another word. For example, color is a hypernym of red.
result
Output: | end |
You are given a question-answer pair. Answer with their type. Pay attention that there may be more than one correct type, but you only have to choose one. In your responses, use of the following types:
(1) Humans: Any individual or group of humans, including fictional ones (e.g., a group or organization of persons , an individual, title of a person, description of a person);
(2) Event: Any phenomenon natural or artificial (e.g., named hurricanes, Battles, Wars, Sports events, Terrorist attacks);
(3) Entity: A thing with distinct and independent existence (Animals, Organs of body, Colors, Inventions, books and other creative pieces, Currency name, Diseases, and medicine, Food, Musical instrument, Languages, Plants, Products, Religions, Sports, Elements and substances, Symbols and signs, Techniques and methods, Equivalent terms, Vehicles);
(4) Facility: Something built for a particular purpose (Buildings, Airports, Highways, Bridges);
(5) Location: A place (Cities, Countries, Mountains, States);
(6) Law: Named documents made into laws (e.g., “the first amendment”, "civil rights act");
(7) Organization: an organized body of people with a particular purpose (Company names, e.g. Google, Cults or terrorist groups, e.g. Al Qaeda);
(8) Date: Absolute or relative dates or periods, bigger than 1 day (Years, Range, e.g. from Monday to Tuesday, or during the 20th century, Approximate time);
(9) Time: Any temporal range/unit that is shorter than a day (e.g., 2 o'clock, 1 pm);
(10) Money: Monetary values, including unit (e.g., "$26", "914$");
(11) Quantity: postcodes or other codes, the number of sth, Ranks, fractions, speed, temperature, size, area, and volume, weight (e.g., "26 degree" "17 inch");
(12) Description: description and abstract concepts (e.g., the definition of something, the manner of an action, reasons);
(13) Abbreviation: expression abbreviated (e.g., AMT = abbreviation of Amazon Mechanical Turk). Don't generate any word that is not mentioned in the list of types (Humans, Event, Entity, Facility, Location, Law, Organization, Date, Time, Money, Quantity, Description, Abbreviation). If you can not associate any of the given types with the provided question and answer pair, respond "Other".
Question: How near to the epicenter was the power plant? (Answer: 20 km). | Law. |
Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.
Q: I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK
A: | run right thrice and walk right twice |
Detailed Instructions: We would like you to classify each of the following sets of argument pairs (discussing Death Penalty) into either SIMILAR or NOT SIMILAR. A pair of arguments is considered SIMILAR if the arguments are about the same FACET (making the same argument), and is considered NOT SIMILAR if they do not have the same FACET. A FACET is a low level issue that often reoccurs in many arguments in support of the author's stance or in attacking the other author's position.
See one example below:
Problem: Sent1: Therefore, people will think twice before they choose to commit a crime and also, the death penalty has been proven to deter the crime rate.
Sent2: i think the death penalty should be abolished because some people are sentenced to deathfor a crime they might have not committed.
Solution: Not similar
Explanation: The two arguments are talking about totally different things. The first one says we should have death penaly since it can deter the crime rate, and the second says we should abolish death penalty since people may not have committed the crime they are accused of.
Problem: Sent1: I am "for" capital punishment... but if a criminal shows a desire for death over a life sentence, I prefer to be sadistic.
Sent2: I do not support the death penalty - but it's not because I feel bad for criminals.
Solution: | Not similar |
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.
Example Input: Content:Председателят на Общински съвет - Плевен Мартин Митев ще подкрепи второто издание на Националната кампания „Великден за всеки“ - Дари празник на баба и дядо. Както и миналата година, и сега той призовава всички общински съветници от Общински съвет - Плевен да се включат в инициативата.Основната идея на Националната кампания „Великден за всеки“, инициирана от омбудсмана Мая Манолова, е всеки българин с финансови възможности да отдели средства и храни за възрастните хора, които няма да получат надбавката по повод големия християнски празник. Правителството отпуска по 40 лв. допълнително на тези, които получават до 314 лв. Идеята на кампанията е да бъдат подпомогнати хора, чиято пенсия надвишава с малко минималния праг. Тази година средствата за кампанията „Великден за всеки“ - „Дари празник на баба и дядо“ се набират по банкова сметка в УниКредит Булбанк, разкрита единствено за целите на кампанията с титуляр Български Червен Кръст (БЧК). IBAN: BG53UNCR70001522802795 Банков код: UNCRBGSF Или с SMS 1255 на стойност 1 лев, освободен от ДДС ОбС-Плевен
Example Output: Председателят на ОбС в Плевен се включва в Националната кампания „Великден за всеки“ - Плевен
Example Input: Content:Илън Мъск: полетните изпитания на Falcon Heavy започват това лято kaldata.com | 03 Април 2017г. Основателят и генерален директор на SpaceX Илън Мъск съобщи, че първият тестов полет на ракетата Falcon Heavy е планиран за края на лятото на 2017 година. Предполага се, че ракетата носител Falcon Heavy ще може да извежда в ниска орбита полезен товар от 55 тона. Специалистите са уверени, че новата ракета може да се използва […] Източник Илън Мъск: полетните изпитания на Falcon Heavy започват това лято var addthis_config = {data_track_clickback:true};
Example Output: Бизнес новини - Илън Мъск: полетните изпитания на Falcon Heavy започват това лято
Example Input: Content:На днешното си заседание Политическият съвет на Реформаторския блок е взел решение да подаде оставка. Повод за това са резултатите на предсрочните парламентарни избори, съобщиха от пресофиса на формацията. В сряда Реформаторският блок свиква Националния координационен съвет, на който ще бъде разгледана оставката и ще бъде направен анализ на изборните резултати. Коалиция Реформаторски блок - Глас народен благодари на всички десни избиратели, които участваха в изборите и най-вече на тези, които подкрепиха коалицията, пише в съобщението. dariknews.bg
Example Output: | Политическият съвет на Реформаторския блок подаде оставка - ШУМ.БГ
|
Given the task definition and input, reply with output. In this task, you will be given a debate topic, along with a sentence from the debate. You should classify the given sentence and choose the type of that sentence. Possible types are explained below.
Policy: This refers to a sentence proposing a specific course of action to be taken. It typically contains modal verbs like "should" and "ought to". It cannot be directly proved with objective evidence, and a proper type of support is a logical reason from which the proposition can be inferred.
Value: This refers to a sentence containing value judgments without making specific claims about what should be done (If so, then it is a Policy sentence.). Because of the subjectivity of value judgments, it cannot be proved directly with objective evidence.
Fact: This refers to an objective proposition expressing or dealing with facts or conditions as perceived without distortion by personal feelings, prejudices, or interpretations. A Fact sentence has a truth value that can be verified with objective evidence that may be available at the time the claim is made; predictions about future are considered unverifiable.
Testimony: This refers to an objective sentence about the author's personal state or experience. Evidence for Testimony is not publicly available in most cases.
topic: University isn't useful compared to college as it is merely theoretical rather than practical
sentence: Depending on the discipline in which one is interested in gaining a degree, university is an invaluable resource.
| Value |
Instructions: This task is to translate a news commentary given in Italian language into Zhuang language. Translate the input statement into the output language while preserving the numberical values, special characters and proper nouns and context of the commentary done.
Input: In primo luogo, le autorità sono intervenute nel periodo 1995-2005, poi di nuovo nel 2008-2010, per mantenere praticamente fisso il tasso di cambio con il dollaro.amp#160; In secondo luogo, i lavoratori cinesi degli stabilimenti costieri sempre più produttivi venivano mal retribuiti (l’economia non ha ancora completato, dopotutto, la transizione da Mao al mercato).
Output: | 自然发生的价格调整过程被推迟了。首先，当局在1995—2005年和2008—1010年两次出手干预，使得美元汇率稳固在一个不变水平上。其次，在生产率不断提升的中国沿海地区，工人并没有获得完全代表劳动价值的工资（毕竟，中国经济尚未全部完成毛泽东主义向市场的过渡）。因此，中国一直以超低价格在向全世界销售商品。 |
Given a sentence in Italian, generate a new Italian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.
Q: È probabile che circondi il motore vicino all'interno di un'auto.
A: | Siete divertenti a trovare il motore vicino all'interno di una macchina. |
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 fine 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 : '$': Dollar Sign, "''": Single Quotes, ',': Comma Symbol, '-LRB-': Left Parantheses, '-RRB-': Right Parantheses, '.': Period, ':': Colon, 'ADD': Email Address, 'AFX': Affix, 'CC': Coordinating conjunction, 'CD': Cardinal Number, 'DT': Determiner, 'EX': Existential there, 'FW': Foreign Word, 'GW': Go with, 'HYPH': Hyphen symbol, 'IN': Preposition or a subordinating conjunction, 'JJ': Adjective, 'JJR': A comparative Adjective, 'JJS': A Superlative Adjective, 'LS': List item Marker, 'MD': Modal, 'NFP': Superfluous punctuation, 'NN': Singular Noun, 'NNP': Singular Proper Noun, 'NNPS': Prural Proper Noun, 'NNS': Prural Noun, 'PDT': Pre-determiner, 'POS': Possessive Ending, 'PRP': Personal pronoun, 'PRP$': Possessive Pronoun, 'RB': Adverb, 'RBR': Comparative Adverb, 'RBS': Superlative Adverb, 'RP': Particle, 'SYM': Symbol, 'TO': To , 'UH': Interjection, 'VB': Base form Verb, 'VBD': Verb in Past tense, 'VBG': Verb in present participle, 'VBN': Verb in past participle, 'VBP': Verb in non-3rd person singular present, 'VBZ': Verb in 3rd person singular present, 'WDT': Wh-determiner, 'WP': Wh-pronoun, 'WP$' Possessive Wh-pronoun, 'WRB': Wh-adverb, 'XX': Unknown, '``': Double backticks.
--------
Question: Sentence: Especially if you are planning to spend couple days with family and kids , which {{ best }} suit you can select ?
Word: best
Answer: JJS
Question: Sentence: Nobody can claim that the interference of Afghanistan ’s neighbours is over , but the elections will do much to strengthen Karzai and deal more firmly with neighbours {{ ’ }} interference .
Word: ’
Answer: POS
Question: Sentence: Make sure {{ if }} you get new fish that they get along with one another .
Word: if
Answer: | IN
|
In this task, you are given two strings A, B. Find the longest common substring in the strings A and B.
Input: Consider Input: ZKMRTxCxbsbX, iovHrMRTxCxbsjv
Output: MRTxCxbs
Input: Consider Input: spUbdWDLWCeqr, vIuHkWDLWCQEPaz
Output: WDLWC
Input: Consider Input: WCinZl, vQinag
| Output: in
|
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.
Example input: Acute pain was observed after taking MTX
Example output: MTX
Example explanation: MTX is a medicine which has been mentioned here, and hence the name should be tagged.
Q: Systemic vasculitis complicating hairy cell leukaemia treatment with cladribine.
A: | cladribine |
You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example "trophy" and "suitcase". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.
| Attribute | triggerword | contrastive triggerword |
| age | old | new |
| altitude | low | high |
| area | small | vast |
| brightness | dark | light |
| clarity | obscure | clear |
| cleanness | dirty | clean |
| complexity | simple | complex |
| cost | cheap | expensive |
| density | sparse | dense |
| depth | shallow | deep |
| distance | near | far |
| electric conductivity | low | high |
| flexibility | rigid | flexible |
| granularity | fine | coarse |
| hardness | soft | hard |
| length | short | long |
| magnitude | small | large |
| mass | small | large |
| odor | weak | strong |
| pressure | low | high |
| resistance | low | high |
| shape | round | sharp |
| shape | flat | spiky |
| size | small | large |
| sound | quiet | loud |
| sound pitch | low | high |
| speed | slow | fast |
| stability | unstable | stable |
| strength | weak | strong |
| temperature | low | high |
| texture | smooth | rough |
| thermal conductivity | low | high |
| thickness | thin | thick |
| volume | small | large |
| weight | light | heavy |
| width | narrow | wide |
| location | in | out |
| location | up | down |
| location | above | below |
| location | on | off |
| location | to | from |
[EX Q]: Context Word: Cartoons.
[EX A]: When John watches TV, he doesn't really like sitcoms, but he'll put on some good cartoons. To him, the _ these days are ridiculous.
[EX Q]: Context Word: hare.
[EX A]: The hare managed to outrun the tractor but not the spitfire because the _ was very slow.
[EX Q]: Context Word: court.
[EX A]: | Adam was summoned to appear before the court to testify in the trial, but the lawyer called a recess and the _ was delayed.
|
You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example "trophy" and "suitcase". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.
| Attribute | triggerword | contrastive triggerword |
| age | old | new |
| altitude | low | high |
| area | small | vast |
| brightness | dark | light |
| clarity | obscure | clear |
| cleanness | dirty | clean |
| complexity | simple | complex |
| cost | cheap | expensive |
| density | sparse | dense |
| depth | shallow | deep |
| distance | near | far |
| electric conductivity | low | high |
| flexibility | rigid | flexible |
| granularity | fine | coarse |
| hardness | soft | hard |
| length | short | long |
| magnitude | small | large |
| mass | small | large |
| odor | weak | strong |
| pressure | low | high |
| resistance | low | high |
| shape | round | sharp |
| shape | flat | spiky |
| size | small | large |
| sound | quiet | loud |
| sound pitch | low | high |
| speed | slow | fast |
| stability | unstable | stable |
| strength | weak | strong |
| temperature | low | high |
| texture | smooth | rough |
| thermal conductivity | low | high |
| thickness | thin | thick |
| volume | small | large |
| weight | light | heavy |
| width | narrow | wide |
| location | in | out |
| location | up | down |
| location | above | below |
| location | on | off |
| location | to | from |
Q: Context Word: goals.
A: | Tim reached his weight loss goals easier when he ate apples instead of bananas because the _ were more filling. |
You will be given a definition of a task first, then some input of the task.
In this task, you are given a country name and you need to return the Top Level Domain (TLD) of the given country. The TLD is the part that follows immediately after the "dot" symbol in a website's address. The output, TLD is represented by a ".", followed by the domain.
Saint Lucia
Output: | .lc |
Detailed Instructions: In this task, you are given a list of integers. You need to find the median of the list of integers and return that as the output. The median is the middle value in the list of numbers such that half of the elements are less than the median and the other half of elements are greater than the median.
Problem:[430, 101, 376, 12, 324, 344, 327, 268, 471, 117, 252, 245, 317, 408, 400, 250, 403, 75, 374, 441, 20, 364, 95, 202, 112]
Solution: | 317 |
Detailed Instructions: 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".
Problem:News Headline: Peacekeeping , African warlords and {Donald Trump}
Edit: pastries
Label: Not Funny
Solution: | No |
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.
Q: password = U!emKYS9
A: 0
****
Q: password = kfUbfQDuGVIF
A: 1
****
Q: password = LczMQ1
A: | 0
****
|
In this task, you will be given a set of steps that are required to answer a specific question. Your job is to generate that question. Each given step refers to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.) Knowing those operations and how they appear in the input may help you generate more accurate questions.
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: #1 return schnauzer
#2 return leash
#3 return #1 that is on #2
#4 return #3 that is in profile
#5 return #4 that is facing leftward
#6 return lattice
#7 return #6 that is white
#8 return If #5 is in front of #7
A: | If a schnauzer on a leash is in profile facing leftward in front of some type of white lattice. |
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'.
Q: Die mogen geen steen op hun hoofd krijgen .
A: | None |
You are given a question-answer pair. Answer with their type. Pay attention that there may be more than one correct type, but you only have to choose one. In your responses, use of the following types:
(1) Humans: Any individual or group of humans, including fictional ones (e.g., a group or organization of persons , an individual, title of a person, description of a person);
(2) Event: Any phenomenon natural or artificial (e.g., named hurricanes, Battles, Wars, Sports events, Terrorist attacks);
(3) Entity: A thing with distinct and independent existence (Animals, Organs of body, Colors, Inventions, books and other creative pieces, Currency name, Diseases, and medicine, Food, Musical instrument, Languages, Plants, Products, Religions, Sports, Elements and substances, Symbols and signs, Techniques and methods, Equivalent terms, Vehicles);
(4) Facility: Something built for a particular purpose (Buildings, Airports, Highways, Bridges);
(5) Location: A place (Cities, Countries, Mountains, States);
(6) Law: Named documents made into laws (e.g., “the first amendment”, "civil rights act");
(7) Organization: an organized body of people with a particular purpose (Company names, e.g. Google, Cults or terrorist groups, e.g. Al Qaeda);
(8) Date: Absolute or relative dates or periods, bigger than 1 day (Years, Range, e.g. from Monday to Tuesday, or during the 20th century, Approximate time);
(9) Time: Any temporal range/unit that is shorter than a day (e.g., 2 o'clock, 1 pm);
(10) Money: Monetary values, including unit (e.g., "$26", "914$");
(11) Quantity: postcodes or other codes, the number of sth, Ranks, fractions, speed, temperature, size, area, and volume, weight (e.g., "26 degree" "17 inch");
(12) Description: description and abstract concepts (e.g., the definition of something, the manner of an action, reasons);
(13) Abbreviation: expression abbreviated (e.g., AMT = abbreviation of Amazon Mechanical Turk). Don't generate any word that is not mentioned in the list of types (Humans, Event, Entity, Facility, Location, Law, Organization, Date, Time, Money, Quantity, Description, Abbreviation). If you can not associate any of the given types with the provided question and answer pair, respond "Other".
Q: Question: What is the motto of the New York City Fire Department? (Answer: New York's Bravest).
A: | Organization. |
Instructions: The provided file includes inquiries about restaurants, and we ask you to translate those to the Finnish language. Please bear in mind the following guidelines 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 fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations.
Input: show me the highest rated restaurant please .
Output: | näytä minulle korkeimman luokituksen omaava ravintola. |
You are given a statement written in Bengali. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement . Output the word from the correct option .
Example input: Statement: ১লা ফেব্রুয়ারী <MASK> ভ্রমণ প্রদর্শক হিসেবে কর্মরত একজন চীনের নাগরিককে দেশে দ্বাদশ করোনার রুগী হিসেবে নিশ্চিত করা হয়। জাপানে করোনায় আক্রান্ত একজন রুগীকে দেখতে গিয়ে তিনি নিজে আক্রান্ত হয়ে পড়েন এবং ১৯শে জানুয়ারী রাজধানী সিওলের গিম্পো আন্তর্জাতিক বিমানবন্দর দিয়ে দেশে প্রবেশ করেন। ২শরা ফেব্রুয়ারী কোরিয়া রোগ নিয়ন্ত্রণ এবং প্রতিরোধ কেন্দ্র (কেসিডিসি) অতিরিক্ত তিনটি মামলা নিশ্চিত করার পরবর্তিতে আক্রান্তদের সংখ্যা মোট পনেরোতে এসে দাঁড়ায়।
Option A: সিঙ্গাপুর
Option B: ভিয়েতনাম
Option C: তাইওয়ান
Option D: জাপানে
Example output: জাপানে
Example explanation: The most suitable word from the given options to replace the <MASK> token is জাপানে, as the statement mentions that the person came from Japan .
Q: Statement: মিরায়াস ২০০৭ সালে <MASK> জ্যেষ্ঠ দলের হয়ে আন্তর্জাতিক পর্যায়ে অভিষেক করেন। তিনি এপর্যন্ত বেলজিয়ামের হয়ে ৫০-এর অধিক ম্যাচ খেলেছেন। তিনি বেলজিয়ামের বেশ কয়েকটি যুব পর্যায়ে বেলজিয়াবের প্রতিনিধিত্ব করেছেন। তিনি ২০০৮ গ্রীষ্মকালীন অলিম্পিক এবং ২০১৪ ফিফা বিশ্বকাপের মতো প্রতিযোগিতায় বেলজিয়ামের হয়ে খেলছেন।
Option A: এভার্টনের
Option B: বেলজিয়ামের
Option C: এভার্টন
Option D: Shatavahana
A: | বেলজিয়ামের |
Detailed Instructions: In this task you will be given a list of integers. You should find the maximum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the largest possible absolute distance.
Q: [1, 69, -28, -86, -84]
A: | 155 |
Detailed Instructions: In this task you will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places.
Q: [57.463, 117.862, 228.694, 221.841, 68.35, 178.129, 13.932, 240.72, 139.1]
A: | 140.677 |
Summarize the following movie reviews:
1. Brilliant when it examines the people who surround his feverish couple, but uncertain when it comes to the lovers themselves.
2. There's no question that this is Lee's most ambitious and successful work so far, but it will be nice if, in the future, he has enough confidence in his story to let down even more of his affectations.
3. I believe that Lee has some interesting things to say about it, but he gets too weighted down by the dubiousness of it all.
4. The result, for the most part, is a provocative, quintessentially Spike symphony.
5. Lee is never content to show one side of the picture and he attempts to address issues that he's not even convinced he's on the wrong side of.
6. It's uneven, but its best moments -- such as Samuel L Jackson's performance -- are amongst Lee's finest achievements on film.
7. Includes a number of memorable set pieces, most notably a visit to a crack den which, accompanied by the epic sound of Stevie Wonder's "Living In The City," is simply unforgettable.
8. Always provocative.
9. Lee brings a shotgun to a knife fight, but his visual energy is undeniably effective, spraying the screen with venom and appalling realities, with most of the feature locked in confessional mode.
10. Snipes, it's clear, is a major actor. | Jungle Fever finds Spike Lee tackling timely sociopolitical themes in typically provocative style, even if the result is sometimes ambitious to a fault. |
We would like you to assess the QUALITY of each of the following argument (discussing Death Penalty) and determine if the argument is Valid or Invalid. A valid argument is clearly interpretable and either expresses an argument, or a premise or a conclusion that can be used in an argument for the topic of death penalty. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of death penalty.
Input: Consider Input: For sheer purposes of punishing a criminal, I don't support the death penalty.
Output: Valid
Input: Consider Input: Turns out they're a lot more reliable than wherever the hell you're pulling your information out of.
Output: Invalid
Input: Consider Input: However, assassinating someone because of a fanatic ideology is not justifiable.
| Output: Invalid
|
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
Q: 1182 # 5672 # 2950 # 8990
A: | -16430 |
The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the no-need strategy, otherwise output No. no-need is a cooperative negotiation strategy. It is used when a participant points out that they do not need an item based on personal context such as suggesting that they have ample water to spare. no-need can directly benefit the opponent since it implies that the item is up for grabs.
Q: Context: 'Ok me too! I am concerned the most with firewood as it is the basis for my camping activities: campfire, story telling, and producing heat. ' 'OK so how about you take 2 firewoods and 1 food' 'That works for me. May I have two waters since I have more of a need of water'
Utterance: 'That works for me since I have the filter!'
A: | Yes |
Given a hotel review and the corresponding polarity of review (i.e., Negative or Positive) identify if the polarity is correct. Write 'true' if it's correct, 'false' otherwise.
Q: Review: Having made regular business trips to Chicago, I decided to stay at the Hotel Monaco Chicago, since it was fairly new and I had a friend that had stayed there. The Lobby was quite small, which surprised me with a name like Monaco. As a matter of fact I found the furnishings to be quite drab.A boy took my luggage and showed me to the suite. It was two rooms, not as spacious as I would have liked, an entertainment room, and a bedroom with a standard television. Can You imagine, I was expecting H.D., but it was just ordinary cable. For $600 a night you would expect a 42 inch set. The bath was ordinary, nothing special, but the bed was a very big King.The view did not take in the Lake, unfortunately, just the Magic Mile. Well, I am starving so time to eat. The restaurant was well appointed, I hope the food was as good. I ordered lamb chops, potatoes au gratin and mint sauce. It was fair. I hope the rest of my trip si better than my accomadations. I would give this hotel a two and a half, but I would not return.
Polarity: Positive
A: | false |
In this task, you are given four sentences: a bot task sentence, a bot role sentence, a user task sentence and a user role sentence. Your job is to classify given sentences into one of the 47 different domains. The domains are: 'UPDATE_CALENDAR', 'PRESENT_IDEAS', 'MOVIE_LISTINGS', 'AUTO_SORT', 'GAME_RULES', 'CONTACT_MANAGER', 'BANK_BOT', 'MUSIC_SUGGESTER', 'CHECK_STATUS', 'PET_ADVICE', 'HOW_TO_BASIC', 'NAME_SUGGESTER', 'QUOTE_OF_THE_DAY_BOT', 'GUINESS_CHECK', 'INSURANCE', 'RESTAURANT_PICKER', 'MAKE_RESTAURANT_RESERVATIONS', 'WEDDING_PLANNER', 'SKI_BOT', 'HOME_BOT', 'PLAY_TIMES', 'BUS_SCHEDULE_BOT', 'WHAT_IS_IT', 'PHONE_PLAN_BOT', 'DECIDER_BOT', 'PHONE_SETTINGS', 'TIME_ZONE', 'LIBRARY_REQUEST', 'UPDATE_CONTACT', 'CATALOGUE_BOT', 'PROMPT_GENERATOR', 'SCAM_LOOKUP', 'SPORTS_INFO', 'POLICY_BOT', 'CITY_INFO', 'APARTMENT_FINDER', 'EVENT_RESERVE', 'SHOPPING', 'EDIT_PLAYLIST', 'LOOK_UP_INFO', 'ORDER_PIZZA', 'WEATHER_CHECK', 'APPOINTMENT_REMINDER', 'GEOGRAPHY', 'STORE_DETAILS', 'AGREEMENT_BOT', 'ALARM_SET'.
Bot's task: Provide the user with the information they request
Bot's role: You are a bot that provides facts about different cities
User's task: Ask what the average life expectancy in Denver is
User's role: You are interacting with a bot that provides facts about different cities | CITY_INFO |
In this task, we ask you to parse restaurant descriptions into a structured data table of key-value pairs. Here are the attributes (keys) and their examples values. You should preserve this order when creating the answer:
name: The Eagle,...
eatType: restaurant, coffee shop,...
food: French, Italian,...
priceRange: cheap, expensive,...
customerRating: 1 of 5 (low), 4 of 5 (high)
area: riverside, city center, ...
familyFriendly: Yes / No
near: Panda Express,...
The output table may contain all or only some of the attributes but must not contain unlisted attributes. For the output to be considered correct, it also must parse all of the attributes existant in the input sentence; in other words, incomplete parsing would be considered incorrect.
Example input: Aromi is an English restaurant in the city centre.
Example output: name[Aromi], eatType[restaurant], food[English], area[city centre]
Example explanation: The output correctly parses all the parseable attributes in the input, no more, no less.
Q: The Rice Boat near the Express by Holiday Inn serves Chinese food at a high price in a family friendly environment with high customer ratings and is located right in the city centre
A: | name[The Rice Boat], food[Chinese], priceRange[more than £30], customer rating[high], area[city centre], familyFriendly[yes], near[Express by Holiday Inn] |
Detailed Instructions: In this task you will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places.
Q: [-81.301, -78.453, 187.627, -34.32, 183.625, 63.108, 63.464, -19.706]
A: | 35.506 |
Teacher: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.
Teacher: Now, understand the problem? Solve this instance: Content:Пролетен празник на маската, маскарадния и сценичния костюм и народната носия ще се проведе във Варна. Това е третото поредно издание на възродения Варненски карнавал, който е бил едно от най-значимите градски събития в периода след Освобождението. Миналата година в инициативата се включиха над 850 участници от цялата страна. Проявата, която тази година минава под знака на титлата на „Варна – Европейска младежка столица“, ще започне на 29-ти април /събота/ от 13.00 ч. на пл. „Св. Св. Кирил и Методий”, с представяне на маски и костюми от състави и индивидуални изпълнители. Около 15:00 ч. участници и зрители ще преминат в шествие през централната част на града до входа на Морската градина, където ще има концерт, забавни игри с награди и атракциони. Около 16:00 ч. гостуващите кукерски групи от цялата страна ще изпълнят характерни ритуали от празничната маскарадна обредност. След това организаторите са предвидили награждаване на победителите от конкурсната програма. Изложба-базар на майстори-занаятчии от цяла България пък ще бъде част от съпътстващата програма – от 10 до 20ч. на входа на Морската градина. Желаещите да се включат в карнавала могат да направят това до 12-ти април на електроненадрес: [email protected]. Заявките и условията за участие в конкурсната програма могат да се изтеглят от сайтовете на дирекция „Култура и духовно развитие”: www.varnaculture.bg и на дирекция „Образование и младежки дейности”: www.varnanamladite.com при Община Варна, както и от официалната фейсбук група Варненски карнавал. За повече информация: Кристин Спасов, гл. експерт „Празници и чествания” тел.: 052/ 820 668; 0885/ 800 862Радка Тодорова, гл. експерт „Духовност и етноси” тел.: 052/ 820 804; 0884/ 990 637 Споделете текущата публикация: Коментирай
Student: | Хайде на карнавал! Vnews новини Варна новини, скандали, анализи, коментари |
You will be given a definition of a task first, then some input of the task.
In this task, you're given text messages in natural language. Your task is to classify those text messages based on their content into two classes: (1) Spam and (2) Ham messages. If the content of the given message is irrelevant to the receiver or is equally relevant to many other potential recipients then it must be labeled as ‘spam’, otherwise, it should be labeled as ‘ham’.
Nope i waiting in sch 4 daddy...
Output: | ham |
Given an entity, a before event, an after event, and an attribute related to the entity, generate a sentence as output. Your sentence should show the changes in the attribute of the entity.
entity: lemon
before: whole
after: cut up
attr: composition | composition of lemon was whole before and cut up afterwards |
Instructions: You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from "sympathetic" to "stern"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.
Input: Context Word: school.
Question: PersonX loves going to school and studying but PersonY does not. _ graduated first in their class.
Answer: PersonX
Output: | PersonX loves going to school and studying but PersonY does not. _ graduated last in their class. |
Detailed Instructions: In this task you will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places.
Q: [16.256, 155.71, 43.059, -64.109, -42.445, 78.725, -12.941, 47.497]
A: | 27.719 |
Detailed Instructions: In mathematics, the absolute value of a number is the non-negative value of that number, without regarding its sign. For example, the absolute value of -2 is 2, and the absolute value of 5 is 5. In this task you will be given a list of numbers and you need to return the element with highest absolute value. If a negative and positive element have the same absolute value you should return the positive element. The absolute value for negative numbers can be found by multiplying them by -1. After finding the element with the maximum absolute value you should return the value of that element before you applied the absolute value.
Q: [-16.179 -43.295 -88.041]
A: | -88.041 |
In this task, you are given a set of paper reviews in English and Spanish language. Based on given reviews, your job is to generate decision, i.e., "accept" or "reject" for the given paper. Note that URLs in the text have been replaced with [Link].
One example is below.
Q: Review_1: En esta investigación se trata un tema que cada vez es más importante en ámbitos académicos y empresariales. Por otra parte, se utilizan métodos de análisis de datos complejos y muy adecuados a los objetivos de la investigación y los autores los que sirven de referencia básica para la investigación son muy adecuados. En la medida en que el objeto material de la investigación es el individuo, entiendo que, cuando se describe la muestra, es conveniente, no sólo describir el perfil de la empresa, sino el perfil del individuo entrevistado (edad, sexo, puesto que ocupa, etc.). • El apartado conclusiones merece, a mi juicio, una mayor atención, que incluya no sólo los resultados de la investigación, sino una discusión más amplia. • Las limitaciones de la investigación hacen referencia al tamaño de la muestra y al tipo de muestreo empleado, pero no hacen referencia a la dimensión del modelo. En este sentido, sería conveniente plantear, como línea de investigación futura, la ampliación del modelo con nuevas variables e indicadores • las referencias bibliográficas son anteriores al año 2009. Sugiero consultar las siguientes o The effect of organizational support on ERP implementation DonHee Lee, Sang M. Lee, David L. Olson, Soong Hwan Chung. Industrial Management + Data Systems. Wembley:2010. Vol. 110, Iss. 2, p. 269-283 o Predicting the behavioral intention to use enterprise resource planning systems :An exploratory extension of the technology acceptance model Fethi Calisir, Cigdem Altin Gumussoy, Armagan Bayram. Management Research News. Patrington:2009. Vol. 32, Iss. 7, p. 597-613 o Organizational adoption of information technologies: Case of enterprise resource planning systems Onur Kerimoglu, Nuri Basoglu, Tugrul Daim. Journal of High Technology Management Research. Greenwich:2008. Vol. 19, Iss. 1, p. 21 Review_2: Abstract: Needs to have a definition of ERP - can't assume the reader knows what this means. Intro: Avoid 1 sentence paragraphs (page 1) The introduction is rather long - it seems to actually be two different sections: an introduction (1st four paragraphs) and 1+ page of background and hypothesis. Overall - at 1.5 pages the intro is rather long for a paper that is 4 pages total. Methodology: I think there are a lot of assumptions in regards to what ERP are and how they work. While the paper is a statistical study, it would have benefited with a context of an actual example. The samples are from small to medium size companies (how many?) with 49 use case (how do these relate?). Results: Discussion is too limited - it assumes that a reader is very familiar with the area, and that may not be the case.
A: accept
Rationale: Reviews seem positive towards paper, hence, the generated label is 'accept'.
Q: Review_1: De forma: • Se recomienda cambiar la palabra “catastros” del título • Problemas de ortografía. Ejemplo: agiles (primer párrafo de la introducción), ingles (sección criterios de inclusión y exclusión) • Se recomienda siempre redactar en tercera persona para textos en español. • Las páginas 6 y 8 del artículo están en blanco. De fondo: • El artículo es claro en su estructura y de fácil lectura. • Se muestra de forma inicial el proceso seguido para el mapeo sistemático y luego de forma ordenada se muestran los resultados al ejecutar cada paso. • Se recomienda cambiar la figura 2 al idioma español, para los casos en que sea posible. • Se aborda un tema interesante y relevante para la comunidad científica y empresarial, y el alcance logrado está acorde con el tipo de productos solicitados para el evento INFONOR. Review_2: El documento presenta un estudio del estado de situación de las técnicas y métodos que el corpus de la investigación ofrece para el tratamiento de requisitos en entornos ágiles. La temática es totalmente actual y coincido con los autores es que hay poco realizado aún y es un campo de explotación. Hay sin embargo, dos comentarios que me gustaría trasladar a los revisores. El primero es que no queda claro porque no han hecho una revisión sistemática de la literatura de manera más formal. La justificación que ofrecen no me parece convincente. Por otro lado, me gustaría que hubiesen desarrollado algo más los trabajos futuros. Tras un buen trabajo no me queda claro qué han aprendido para ponerlo en práctica en su futura investigación.
A: | accept |
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."
Let me give you an example: Beginning: Lauren finished her late night shift at the bar feeling tired. Middle: Lauren took a long hot bath when she got home. Ending: Lauren's husband was glad to see her feeling refreshed.
The answer to this example can be: Lauren's husband took a long hot bath when he got home.
Here is why: If a person takes a bath, another person's tiredness is not reduced.
OK. solve this:
Beginning: Johann decides he wants to make dinner. Middle: He was very excited to cook. Ending: Johann is disappointed that he has overcooked his kale for dinner.
Answer: | He was an exciting crook. |
Instructions: In medical studies, the efficacy of medical treatments (called interventions) is evaluated within a group of study participants. You will be given a sentence of a study report in which your task is to list the phrases that describe the intervention(s) of the study. You should list the phrase in the same order that they appear in the text, separated by commas. If no information about the interventions is mentioned, just answer with "not found". Interventions are: a specific drug, surgery, talking therapy, a lifestyle modification, control or placebo treatment. Do not include details, dosages, frequency and duration, intervention mentions that are not in an informative span of text.
Input: Overall , 13 patients ( 46.4 % ) had detrusor overactivity and 14 ( 50 % ) had decreased bladder capacity .
Output: | not found |
We would like you to classify each of the following sets of argument pairs (discussing Death Penalty) into either SIMILAR or NOT SIMILAR. A pair of arguments is considered SIMILAR if the arguments are about the same FACET (making the same argument), and is considered NOT SIMILAR if they do not have the same FACET. A FACET is a low level issue that often reoccurs in many arguments in support of the author's stance or in attacking the other author's position.
Ex Input:
Sent1: if you execute a pickpocket or give him life imprisonment, then you would have one less thief to worry about but I think we agree that that would be excessive).
Sent2: Also, I wonder if a criminal thinks of the punishment when he commits the crime - if he were counting on being punished, he wouldn't have done it.
Ex Output:
Not similar
Ex Input:
Sent1: so you weigh whatever monetary savings (if any) over the life of someone found innocent after conviction (even if rare)?
Sent2: After all, the person you're torturing may actually be innocent.
Ex Output:
Not similar
Ex Input:
Sent1: People generally think that the death penalty is worse than life without parole (certainly most criminals seem to think so).
Sent2: Most people who would be deterred already seem to be deterred by life without parole as a punishment.
Ex Output:
| Not similar
|
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
Q: ['M', '4957', 'E', 'u', '7785', 'X', 'x', '9349', 't', '7707', '7119', '1115', 'X', '9635', 'N', 's', '6485', 'M', '5723', '3397', '3561', '6749', '8195', '7325', 'X', 'E', '2275']
A: | 12 |
You are given a target race, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.
One example is below.
Q: Target: hispanic
My professor is a hispanic man. He came here illegally.
A: stereotype
Rationale: This is a stereotype because not every hispanic person has moved to a different country and is undocumented.
Q: Target: Sierra Leon
Sierra Leon is located in western africa. some of the most beautiful diamonds come from here.
A: | stereotype |
Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
One example: ['hey', 'everybody', 'ivan', 'from', 'weights', 'and', 'biases', 'here', 'in', 'this', 'video', "i'd"]
Solution is here: ['CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'CASE_DIFF', 'UNKNOWN_TYPE_DIFF', 'CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF']
Explanation: This sentence is a good example since the input stream is a grammatically incorrect statement and the output labels correctly classify the words that were incorrect.
Now, solve this: ['over', 'many', 'videos', 'now', "we've", 'been', 'talking', 'about', 'how', 'every', 'interstellar', 'object', 'is', 'moving', 'away', 'from', 'earth', 'and', "we've", 'also', 'been', 'talking', 'about', 'how', 'the', 'further', 'something', 'is', 'away', 'from', 'Earth', 'the', 'faster', "it's", 'moving', 'what', 'I', 'want', 'to', 'do', 'in', 'this', 'video', 'is', 'to', 'put', 'a', 'little', 'bit', 'of', 'a', 'few', 'numbers', 'behind', '', 'or', 'even', 'better', 'conceptualize', 'what', "we've", 'been', 'talking', 'about', 'so', 'one', 'way', 'to', 'think', 'about', 'it', 'is', 'that', 'if', 'at', 'an', 'early', 'stage', 'in', 'the', 'universe', 'I', 'were', 'to', 'pick', 'some', 'points', 'so', "that's", 'one', 'point', 'another', 'point', 'another', 'point', 'another', 'point', 'let', 'me', 'just']
Solution: | ['CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF'] |
Detailed Instructions: Given a concept word, generate a hypernym for it. A hypernym is a superordinate, i.e. a word with a broad meaning constituting a category, that generalizes another word. For example, color is a hypernym of red.
See one example below:
Problem: crystal
Solution: rock
Explanation: A crystal is a type of rock, so rock is a valid hypernym output.
Problem: puppy
Solution: | animal |
Detailed Instructions: 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...'.
Q: Prompt: We shared an experience in our apartment last night where somebody may or may not have been there.
Response: He threw a rock and knocked out a cop.
A: | no |
In this task, you will be given a set of steps that are required to answer a specific question. Your job is to generate that question. Each given step refers to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.) Knowing those operations and how they appear in the input may help you generate more accurate questions.
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].
#1 return the boy in the striped pajamas
#2 return shmuel of #1
#3 return who played #2 | who played shmuel in the boy in the striped pajamas? |
In medical studies, the efficacy of medical treatments (called interventions) is evaluated within a group of study participants. You will be given a sentence of a study report in which your task is to list the phrases that describe the intervention(s) of the study. You should list the phrase in the same order that they appear in the text, separated by commas. If no information about the interventions is mentioned, just answer with "not found". Interventions are: a specific drug, surgery, talking therapy, a lifestyle modification, control or placebo treatment. Do not include details, dosages, frequency and duration, intervention mentions that are not in an informative span of text.
Example Input: Data analyzed was from a phase III , randomized clinical trial of DOX ( 60 mg/m ( 2 ) every 3 weeks ) or PLD ( 50 mg/m ( 2 ) every 4 weeks ) for the first line therapy for MBC ( n = 509 ) ( O'Brien et al , Ann Oncol .
Example Output: DOX, PLD
Example Input: Ascaris and growth rates : a randomized trial of treatment .
Example Output: not found
Example Input: 21 patients ( age 0-2 months ) and 40 healthy infants ( age 0-2 months ) were investigated .
Example Output: | not found
|
You are given first 5 messages from a series of message exchanges between 2 persons playing the game of Diplomacy which is an American strategic board game. You need to generate the next message. The message should be generated such that it fits the context seen so far. Avoid the text that is (i) tangent to the context, (ii) repeats the context.
Example input: ['Heyyyy Turkey', 'Whatcha thinking re: start of the game?', "It kind of depends. I'll probably want to stop Russia from advancing south", "I'm kind of afraid of Austria and Russia teaming together on me", 'I mean if that happens you’re donezos']
Example output: What vibes are you getting from each of them?
Example explanation: The message fits the context as it asks for the vibes of 2 of them which refers to 2 countries: Austria and Russia in the second last message. Thus it is a positive example.
Q: ["I've been on both the giving and receiving ends of multiple games in which Austria, Italy, and Russia decided that their games would be much simpler if there wasn't a Turkey around, and it always was. I propose that we start the game off by coordinating a removal of Turkey before moving on to other priorities.", 'I think that would be a great idea. How would you propose we split up their territories afterward? And could I count on your support should Germany move towards me?', "Yeah, I'd definitely have your back against Germany. As for the split... I get Ankara and Rumania, you get Bulgaria and Constantinople, and Italy gets Greece and Smyrna?", "Fantastic. I'd personally prefer Rumania/Bulgaria and you can have Constantinople/Ankara.", 'That also works.']
A: | Ah SHIT, I'm sorry, I meant to update my orders to fix the Galicia move but it didn't go through. I'll be sending Galicia to Rumania this turn, and then turning Rumania over to you next turn. Promise. |
You will be given a definition of a task first, then some input of the task.
Find the movie name from the given conversation. If the movie name is not found give output as "unknown"
ASSISTANT: What kind of movies to you like, and why do you like this type of movie? , USER: Fantasy movies. , USER: I like fantasy movies because they , USER: They make me see the world from They make me see what's what's beyond planet Earth. , ASSISTANT: can you give me one more reason? , USER: They are educated movies. , ASSISTANT: Can you name a particular movie that you like? , USER: Space Jam.
Output: | Space Jam |
Detailed Instructions: In this task you will be given an arithmetic operation in Italian and you have to find its answer. The operations 'addition' and 'subtraction' have been replaced with their italian translations i.e you need to perform addition when you see 'aggiunta' and subtraction in case of 'sottrazione'.
Q: 6223 sottrazione 8157 aggiunta 9146 sottrazione 4191 sottrazione 1509 aggiunta 3990
A: | 5502 |
Detailed Instructions: In this task, you are given two strings A,B. Find the longer of the two lists, convert it to lowercase, and return all the unique alphabets used in it. The two input strings are never equal.
Q: SUNqhhTdGgPS, rAKbdhTdGgZoG
A: | a, b, d, g, h, k, o, r, t, z |
Instructions: Write a fact related to the given fact, based on the given topic word. Note that, your fact should have at least one word in common with the given fact. All facts in this task refer to scientific facts. Your related fact must form a chain with the given fact. Chains form when two facts connect together to produce the third fact. An example of a chain is: "pesticides cause pollution" (given fact) + "pollution can harm animals" (related fact) → "pesticides can harm animals" (connected chain). Avoid creating simple paraphrases of the given fact. While your generated fact should be related to the input fact, they must describe slightly different scientific phenomena. It's okay if your related fact includes some irrelevant information, provided that it has some overlap with the given fact and it contains some words corresponding to the provided topic.
Input: Fact: Energy is passed up a food chain or web from lower to higher trophic levels.
Topic: energy is organic.
Output: | All organisms require energy. |
Given a concept word, generate a hypernym for it. A hypernym is a superordinate, i.e. a word with a broad meaning constituting a category, that generalizes another word. For example, color is a hypernym of red.
Ex Input:
pit
Ex Output:
cavity
Ex Input:
coffee
Ex Output:
tree
Ex Input:
ink
Ex Output:
| write
|
Given the task definition and input, reply with output. We would like you to classify each of the following sets of argument pairs (discussing Gay Marriage) into either SIMILAR or NOT SIMILAR. A pair of arguments is considered SIMILAR if the arguments are about the same FACET (making the same argument), and is considered NOT SIMILAR if they do not have the same FACET. A FACET is a low level issue that often reoccurs in many arguments in support of the author's stance or in attacking the other author's position.
Sent1: Everyone has the right to marry someone of the opposite sex, and with gay marriage, everyone will have the right to marry someone of the same AND opposite sex.
Sent2: However it should be recognised that gay marriage is not the same as opposite sex marriage.
| Not similar |
Read the given text and if it has abusive content then indicate via "yes". Otherwise indicate via"no".
We consider the content to be abusive if it contains any of the following instances: (1) Identity Directed Abuse (e.g., Content which contains a negative statement made against an identity. An identity is a social category that relates to a fundamental aspect of individuals community, socio-demographics, position or self-representation) (2) Affiliation Directed Abuse (e.g., Content which express negativity against an affiliation. We define affiliation as a (more or less) voluntary association with a collective. Affiliations include but are not limited to: memberships (e.g. Trade unions), party memberships (e.g. Republicans), political affiliations (e.g. Right-wing people) and occupations (e.g. Doctors).) (3) Person Directed Abuse (e.g., Content which directs negativity against an identifiable person, who is either part of the conversation thread or is named. Person-directed abuse includes serious character based attacks, such as accusing the person of lying, as well as aggression, insults and menacing language.) and (4) Counter Speech (e.g., Content which challenges, condemns or calls out the abusive language of others.). Note that URLs in the text have been replaced with [Link].
Q: Fuckin' lol thought y'all were talking about Return of the King for a minute with that acronym My dumb ass was over here like "Cao Cao... I guess that'd be a hobbit? Idk"
A: no
****
Q: They're going to get supplies for ceiling rope.
A: yes
****
Q: I'm hydrophobic.
A: | no
****
|
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 dog in the image on the left is standing outside.
A: | #1 return the image on the left
#2 return dog in #1
#3 return #2 that is standing
#4 return if #3 is outside |
Given an adjective, generate its antonym. An antonym of a word is a word opposite in meaning to it.
Example input: able
Example output: unable
Example explanation: The output is correct as able and unable are opposities of each other in meaning.
Q: acute
A: | obtuse |
Given news headlines and an edited word. The original sentence has word within given format {word}. Create new headlines by replacing {word} in the original sentence with edit word. Classify news headlines into "Funny" and "Not Funny" that have been modified by humans using an edit word to make them funny.
Example: News Headline: France is ‘ hunting down its citizens who joined {Isis} without trial in Iraq
Edit: twins
Example solution: Not Funny
Example explanation: The edited sentence is not making much sense, therefore it's not funny.
Problem: News Headline: CBO : {Trump} is making Obamacare premiums more expensive
Edit: cupcake
| Solution: Not Funny |
End of preview. Expand
in Data Studio
- Downloads last month
- 38
Size of downloaded dataset files:
271 MB
Size of the auto-converted Parquet files:
271 MB
Number of rows:
377,695