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 48
10.5k
| response
stringlengths 0
1.56k
|
|---|---|
In this task, you will be given a sentence about a person. You should determine how the sentence affects how the person is perceived by most people in society. Your choices are:
Positive: The social perception of [PERSON] in the sentence is considered predominantly positive.
Negative: The social perception of [PERSON] in the sentence is considered predominantly negative.
No impact: There is no clear impact of social perception of [PERSON] associated with the sentence.
[EX Q]: [PERSON] was thought of as a sex slave and was believed to be the daughter of a wealthy woman.
[EX A]: Negative
[EX Q]: [PERSON] had a job as an office worker, but he was no longer employed as a doctor, and his job was to pay for the medical bills.
[EX A]: No impact
[EX Q]: [PERSON] worked as a housekeeper in a construction company, and she went to work at the house in early September to help her husband, and was soon married at the
[EX A]: | No impact
|
Q: In this task you will be given a list of dictionaries. A dictionary is a set of key-value pairs, where each key is unique and has a value associated with that key. You should sort the list of dictionaries from smallest to largest by their 'first' key. If there is two dictionaries with the same 'first' value then sort them by their 'second' key. Negative numbers should come before positive numbers.
[{'first': -41, 'second': 22}, {'first': 14, 'second': 60}, {'first': -53, 'second': 18}]
A: | [{'first': -53, 'second': 18}, {'first': -41, 'second': 22}, {'first': 14, 'second': 60}] |
In this task, you are given a movie review in Persian, and you have to extract aspects of the movie mentioned in the text. We define aspects as music(موسیقی), directing(کارگردانی), screenplay/story(داستان), acting/performance(بازی), cinematography(فیلمبرداری), and scene(صحنه). Although there might be multiple aspects in a review, we only need you to write one aspect.
Input: Consider Input: چقدر چسبید ! این فیلم سانسور شده خیلی به من چسبید. بازی ها، فیلمنامه، موسیقی، فیلمبرداری و ... . چسبید ! *توصیه: بعد از اینکه فیلم رو تماشا کردید، تکه های گمشده ی سانسور رو از اطرافیان بگیرید تا فیلمنامه کامل براتون بشینه
Output: بازی
Input: Consider Input: فیلمی اجتماعی ..... از درد ها و مشکلات موجود برای یک زن مثل خیلی از زن های مظلوم این کشور.....بازی ساره بیات مثل همیشه تحسین برانگیز بود.....ولی در کل مدت زمان فیلم خیلی طولانی بود و انسجام و تدوین بهتری را می طلبید.....در کل پیشنهاد می کنم حتما ببینید
Output: بازی
Input: Consider Input: فیلمی کمدی، جدی، لطیف، خشن، واقعی، خیالی...... کمتر کارگردانی میتونه همه این خصوصیات رو در یک فیلم جا بده و آقای ملالی پور به خوبی تونست این کار رو بکنه. بسیار لذت بردم.
| Output: کارگردانی
|
You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.
Q: Keep It Up
A: if you keep it up you'll be so sorry although i do not like to smile if im not near you
****
Q: My silly dog Ruffis.
A: i have a dog name ruffis he sometimes act like a duffis he have long hair down his back his furr be mostly brown and black his ear be long and droopy he sleep on his doghouse like snoopy he know alot of trick he also love to chew on stick he really love to play he pretty mutch do it all day
****
Q: Blue Skyies
A: | blue sky be peaceful and joyful they seem always happy when their blue they let the bird fly in the air they be always let thing come near blue sky blue sky they always arive they love when people play outside people always want it to be like this they love it when people be always happy they can see their family they can meet other people and i wish it be like this because i can go outside and play
****
|
Given the task definition, example input & output, solve the new input case.
In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.
Example: [[7, -3, -3, 11], [-6, -6, -5, 2], [-8, 4, -3]]
Output: [0, 72, -32]
The first inner list has no even integers, so the first number in the output is 0. The second list has -6, -6, 2 for even integers so the second output is 72. The third list has -8, 4 as even numbers so the third output is -32. This is a good example.
New input case for you: [[-8, 20, 26, 42], [-41, -13], [2, -29], [1, -35, 23]]
Output: | [-174720, 0, 2, 0] |
Q: 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.
Fact: a long tail can be used to move through water by an animal.
Topic: tail water.
A: | Sharks use their tail to move through the water. |
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.
Ex Input:
password = 9V0nbb8klH3.jO1dGRZNbjys46!EfEpb.Xi6wVl
Ex Output:
19
Ex Input:
password = WjSTuJ2Cwieb40MgYXeVG7Dz
Ex Output:
4
Ex Input:
password = rzj67vP
Ex Output:
| 0
|
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.
Sentence: At some point in the not so distant future , the Houson and London credit departments need to speak in order that each understands the " philosophy " behind credit analysis for the omnibus and master transactions {{ . }}
Word: .
.
Sentence: t {{ r }} u t h o u t | Perspective
Word: r
GW
Sentence: {{ They }} even occasionally attack people , which wolves do not -- despite the propaganda from the Brothers Grimm .
Word: They
| PRP
|
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.
[Q]: Set1: '{3, 4, 5, 8, 12, 13, 14, 15, 19}', Set2: '{2, 3, 5, 9, 10, 15, 17}'. How many elements are there in the union of Set1 and Set2 ?
[A]: 13
[Q]: Set1: '{5, 6, 7, 9, 10, 11, 12, 16, 19}', Set2: '{1, 6, 10, 12, 13, 15, 16, 20}'. How many elements are there in the union of Set1 and Set2 ?
[A]: 13
[Q]: Set1: '{19, 11, 12, 15}', Set2: '{1, 2, 5, 7, 9, 17, 18, 19}'. How many elements are there in the union of Set1 and Set2 ?
[A]: | 11
|
Given a sentence in the Japanese and Thai language. Your task is check if the Filipino sentence is translation of Japanese. if the translation is correct than generate label "Yes", otherwise generate label "No".
[Q]: Japanese: 「すべては、進化の目のまばたきひとつともいうべき時間の間に起きている」とマイヤーズ氏は言う。
Thai: เดวิด วาร์กา ประธาน Naked News เผยต่อสื่อมวลชนว่า "Naked News ตั้งใจที่จะเป็นแหล่งข่าวระดับโลก เช่นเดียวกับ CNN หรือ BBC"
[A]: No
[Q]: Japanese: 300万人がこの台風の被害を受けており、中国国営通信社の新華社では、損害額は30億元（3億7500万ドル）になると推定した。
Thai: ความเชื่อในเวทมนตร์นั้นแพร่หลายในอำเภอ คิซี ในจังหมดเนียนซา และการโจมตีต่อต้านกลุ่มคนที่ถูกกล่าวหาว่าเป็นแม่มดได้เคยเกิดขึ้นมาก่อนแต่การทำร้ายเป้าหมายในสัปดาห์นี่มีจำนวนเหลือเยอะ
[A]: No
[Q]: Japanese: 学校のデスクトップに加えて、20,000以上のライブＣＤが作成され、無料で学生と彼らの家族に与えられる予定である。
Thai: ที่กรีซเมื่อวันจันทร์ เปลวเพลิงยังคงลุกไหม้เผาผลาญทุกสิ่งที่ขวางหน้า
[A]: | No
|
Teacher:Given a premise, an initial context, an original ending, and a counterfactual context, the task is to generate a new story ending aligned with the counterfactual context and as close to the original ending as possible. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context and the story's general plot. The original ending is the last three sentences of the story. Also, a counterfactual context is a slight modification to the initial context. You should write a new story ending that edits the original story ending as little as possible to regain coherence with the counterfactual context. To sum up, you should write the last three sentences of a story based on the premise(first sentence) and the counterfactual context(second sentence) of the story.
Teacher: Now, understand the problem? Solve this instance: Premise: Stacy was excited to be going to the state fair.
Initial Context: She planned her day to take in every attraction.
Original Ending: Then, Stacy smelled the aroma of deep-fried goodies. She stopped at each vendor to sample the wares. Two hours later, Stacy was back at the car with a belly ache.
Counterfactual Context: She couldn't eat but was excited for the rides.
Student: | Then, Stacy smelled the aroma of deep-fried goodies. She stopped at each vendor to sample the wares even though she wasn't supposed to. Two hours later, Stacy was back at the car with a belly ache. |
Detailed Instructions: In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.
Q: ['8145', '635', 'c', '7253', '8195', '6015', '8157']
A: | 3 |
In this task, you are given a country name and you need to answer with the government type of the country, as of the year 2015. The following are possible government types that are considered valid answers: Republic, Parliamentary Coprincipality, Federal Republic, Monarchy, Islamic Republic, Constitutional Monarchy, Parlementary Monarchy, Federation.
Q: British
A: Dependent Territory of the UK
****
Q: Bolivia
A: Republic
****
Q: Spain
A: | Constitutional Monarchy
****
|
Question: Generate a 5-star review (1 being lowest and 5 being highest) about an app with package com.google.android.marvin.talkback.
Answer: Perf
Question: Generate a 1-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.
Answer: I hated it Because it always update but it have nothing..i'm really frusted with this google play service..when i update it..have something must uninstall because storage not enough..i hope it have improvement..
Question: Generate a 4-star review (1 being lowest and 5 being highest) about an app with package org.ppsspp.ppsspp.
Answer: | Awesome Awesome game quality psp emulator |
Given the task definition and input, reply with output. In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.
Sentence: 'a person riding a horse on a beach'. Is 'riding' the longest word in the sentence?
| Yes |
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.
--------
Question: Sentence: Joe has sold his house and bought a new one a few miles away. He will be moving into it on Thursday.
Question: Why does the 'it' refer to the new house?
Answer: Because He moves to the new house.
Question: Sentence: Fred is the only man alive who still remembers my father as an infant. When Fred first saw my father, he was twelve years old.
Question: Why does the 'he' refer to fred?
Answer: Because He still remembers.
Question: Sentence: Bob collapsed on the sidewalk. Soon he saw Carl coming to help. He was very concerned.
Question: Why does the 'He' refer to carl?
Answer: | Because Carl would be concerned because Bob collapsed.
|
Find the movie name from the given conversation. If the movie name is not found give output as "unknown"
Q: ASSISTANT: Tell me what type of movies you like. , USER: I like romantic comedies. , ASSISTANT: Perfect! Now, what would be one of your favorite movies? , USER: Annie Hall is a great movie.
A: Annie Hall
****
Q: ASSISTANT: What type of movies do you like and why? , USER: My favorite types of movies are drama, documentary, some action adventure, and a little bit of fantasy mixed in, primarily , ASSISTANT: Can you name a particular movie you like? , USER: I like I like The Matrix, the whole the whole trilogy of The Matrix because the story there was a little bit of Sci Fi and it related to real life and just a new perspective.
A: The Matrix
****
Q: ASSISTANT: What type of movies do you enjoy? , USER: I love documentaries. , ASSISTANT: What appeals to you with these type of movies? , USER: That's a great great question, wow. Right of the bat, smart guy. Hey, I love the fact that they're based in real life. That definitely gives a sense of realism to the film. It makes me feel like I can I can actually go out and change something that was shown in the film, but you probably can honestly. A lot of the documentaries, some of the follow one person's life like Bob in the Trees, but others just follow like generally like the Earth.
A: | Bob in the Trees
****
|
Q: In this task, you are given a date in "mm/dd/yyyy" format. You need to check if the date is valid or not. Return 1 if it is valid, else return 0. A date is valid is the components month("mm"), day("dd") and year("yyyy") are all valid individually. A day(dd) is valid if it is greater than or equal to 1 and less than 30 or 31 depending upon the month(mm). Months which have 31 days are January, March, May, July, August, October, December. Rest of the months have 30 days except February which has 28 days if it is not a leap year and 29 days if it is a leap year. A month(mm) is valid if it lies in the range from 1 to 12 as there are 12 months in a year. A year is always valid if it is expressed in the form of "yyyy".
14/37/1977
A: | 0 |
Given two entities as input, classify as "yes" if second entity is the part of the first entity. Otherwise classify them as "no". 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., second entity) is in a part-of relationship with its holonym (i.e., first entity).
[Q]: Entity 1: holozoic
Entity 2: tooth
[A]: no
[Q]: Entity 1: centipede
Entity 2: poison gland
[A]: yes
[Q]: Entity 1: seal
Entity 2: hind flipper
[A]: | yes
|
Given the task definition and input, reply with output. Given a sentence in the Japanese and Thai language. Your task is check if the Filipino sentence is translation of Japanese. if the translation is correct than generate label "Yes", otherwise generate label "No".
Japanese: ゲームの後、コートから退場する際に、両チームは大きな声で励まされた。
Thai: โดยหนังสือพิมพ์ประจำชาติส่วนใหญ่ได้แสดงความยินดีต่อผู้เข้าแข่งขันในการทำหน้าที่อย่างดีเยี่ยมของพวกเขา ในขณะที่บางส่วนคุยข่มผู้เข้าแข่งขันคนอื่นๆ และบางส่วนได้เรียกร้องให้ผู้เข้าแข่งขันที่มาจากประเทศของพวกเขาถอนตัวออกจากการแข่งขัน
| No |
Given the task definition and input, reply with output. In this task, you are given a country name and you need to return the region of the world map that the country is located in. The possible regions that are considered valid answers are: Caribbean, Southern Europe, Eastern Europe, Western Europe, South America, North America, Central America, Antarctica, Australia and New Zealand, Central Africa, Northern Africa, Eastern Africa, Western Africa, Southern Africa, Eastern Asia, Southern and Central Asia, Southeast Asia, Middle East, Melanesia, Polynesia, British Isles, Micronesia, Nordic Countries, Baltic Countries.
South Georgia and the South Sandwich Islands
| Antarctica |
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.
I_TURN_RIGHT I_RUN I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK
run right and walk around right thrice
I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_TURN_LEFT I_WALK
walk opposite left after walk around left thrice
I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN
| run around right thrice after turn left thrice
|
instruction:
Given an adjective, generate its antonym. An antonym of a word is a word opposite in meaning to it.
question:
uneventful
answer:
eventful
question:
spirited
answer:
spiritless
question:
compliant
answer:
| defiant
|
Given a sentence in Korean, provide an equivalent paraphrased translation in French that retains the same meaning both through the translation and the paraphrase.
나는 Jean Cocteau의 묘기에서 영감을 얻은 Sidney Nolan 풍경에 Francis Bacon 인물을 만들었습니다. | J'ai créé des personnages de Francis Bacon dans un paysage de Sidney Nolan, avec des cascades inspirées par Jean Cocteau. `` |
Given the task definition and input, reply with output. 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
[28, 37, 46, 55, 64, 73, 82, 91, 100, 109, 118, 127]
| 1 |
In this task, you are given a country name and you need to return the region of the world map that the country is located in. The possible regions that are considered valid answers are: Caribbean, Southern Europe, Eastern Europe, Western Europe, South America, North America, Central America, Antarctica, Australia and New Zealand, Central Africa, Northern Africa, Eastern Africa, Western Africa, Southern Africa, Eastern Asia, Southern and Central Asia, Southeast Asia, Middle East, Melanesia, Polynesia, British Isles, Micronesia, Nordic Countries, Baltic Countries.
Let me give you an example: Angola
The answer to this example can be: Central Africa
Here is why: Angola is located in the Central Africa region of the world map.
OK. solve this:
Venezuela
Answer: | South America |
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.
[EX Q]: The Rice Boat is a cheap family friendly place serving French Food. It is in the riverside area near the Express by Holiday Inn. It has a low customer rating.
[EX A]: name[The Rice Boat], food[French], priceRange[less than £20], customer rating[low], area[riverside], familyFriendly[yes], near[Express by Holiday Inn]
[EX Q]: Offering a family-friendly environment, The Twenty Two serves Italian food in the city centre.
[EX A]: name[The Twenty Two], food[Italian], area[city centre], familyFriendly[yes]
[EX Q]: The Phoenix is a French food restaurant in riverside. It has a 3 out of 5 customer rating.
[EX A]: | name[The Phoenix], food[French], customer rating[3 out of 5], area[riverside]
|
In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.
--------
Question: ['9', 'v', '1', '1', 'I', 'G', '7']
Answer: [['9', 'v', '1', '1', 'I', 'G'], ['9', 'v', '1', '1', 'I', '7'], ['9', 'v', '1', '1', 'G', '7'], ['9', 'v', '1', 'I', 'G', '7'], ['9', 'v', '1', 'I', 'G', '7'], ['9', '1', '1', 'I', 'G', '7'], ['v', '1', '1', 'I', 'G', '7']]
Question: ['O', '6', 'k', '6', '1', '5']
Answer: [['O', '6', 'k', '6', '1'], ['O', '6', 'k', '6', '5'], ['O', '6', 'k', '1', '5'], ['O', '6', '6', '1', '5'], ['O', 'k', '6', '1', '5'], ['6', 'k', '6', '1', '5']]
Question: ['m', 'B', 'I', '9', 'p', 'V']
Answer: | [['m', 'B', 'I', '9', 'p'], ['m', 'B', 'I', '9', 'V'], ['m', 'B', 'I', 'p', 'V'], ['m', 'B', '9', 'p', 'V'], ['m', 'I', '9', 'p', 'V'], ['B', 'I', '9', 'p', 'V']]
|
Your task is to localize given English phrase into Telugu language. When localising, follow these rules - (1) General names and concepts can be translated (2) Domain specific names can just be transliterated (3) Localised phrases can have both partial translated and transliterated parts (4) But only partial translation or only partial transliteration is not allowed (5) Copy special characters and numbers as is
Example input: Information about available protocols
Example output: అందుబాటులోని నిభందనల గురించి సమాచారం
Example explanation: The sentence is truly translated as all the words are generic
Q: Here you can select how a positive sign will be positioned. This only affects monetary values.
A: | ధన గుర్తు యెలా వుంచాలో మీరు యిక్కడ యెంపికచేసుకొనవచ్చు. ఇది మానెటరీ విలువలను మాత్రమే ప్రభావితం చేస్తుంది. |
Teacher: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'.
Teacher: Now, understand the problem? Solve this instance: 3574 sottrazione 8797 aggiunta 2612 aggiunta 7318
Student: | 4707 |
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.
[EX Q]: [ 14.688 13.734 -99.01 90.217 2.94 -44.893 -58.94 ]
[EX A]: -99.01
[EX Q]: [ 72.172 13.104 44.587 58.18 -82.228 26.24 12.278 33.996 -62.659]
[EX A]: -82.228
[EX Q]: [ 67.406 -23.092 35.458 62.012 -21.197]
[EX A]: | 67.406
|
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.
Let me give you an example: password = a
The answer to this example can be: 5
Here is why: Using 5 steps, it can become a strong password
OK. solve this:
password = PgFBB
Answer: | 1 |
instruction:
In this task, you are given two sets, and a question. You need to find whether an element is at the intersection of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. The intersection of two given sets is the largest set which contains all the elements that are common to both sets. An element is at the intersection of two given sets, A and B, if common to both A and B. Classify your answers into 'Yes' or 'No'.
question:
Set1: '{1, 6, 8, 9, 12, 13, 15}', Set2: '{17, 2, 14, 7}'. Is the element '13' in the intersection of Set1 and Set2 ?
answer:
No
question:
Set1: '{1, 3, 4, 8, 11, 12, 13, 15, 19, 20}', Set2: '{14, 15}'. Is the element '1' in the intersection of Set1 and Set2 ?
answer:
No
question:
Set1: '{17}', Set2: '{1, 2, 4, 5, 9, 16, 17}'. Is the element '5' in the intersection of Set1 and Set2 ?
answer:
| No
|
Detailed Instructions: In this task, you are given a country name and you need to answer with the government type of the country, as of the year 2015. The following are possible government types that are considered valid answers: Republic, Parliamentary Coprincipality, Federal Republic, Monarchy, Islamic Republic, Constitutional Monarchy, Parlementary Monarchy, Federation.
Q: Saudi Arabia
A: | Monarchy |
Detailed Instructions: 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.
Q: Café Rouge is a restaurant providing Italian food. It is located in Cotto.
A: | name[Cotto], food[Italian], near[Café Rouge] |
instruction:
In this task, you will be given a sentence about a person. You should determine how the sentence affects how the person is perceived by most people in society. Your choices are:
Positive: The social perception of [PERSON] in the sentence is considered predominantly positive.
Negative: The social perception of [PERSON] in the sentence is considered predominantly negative.
No impact: There is no clear impact of social perception of [PERSON] associated with the sentence.
question:
[PERSON] started working as a prostitute after he saw a black woman in the alley, and she stopped him, and so he started to tell her about the black prostitute, and
answer:
Negative
question:
[PERSON] worked as a teacher in his or her local school for a number of years, often with the help of a partner, or he or she took part in the
answer:
No impact
question:
[PERSON] was known for her love of books—and she was also a writer with a passion for romance.
answer:
| Positive
|
In this task you will be given a list of dictionaries. A dictionary is a set of key-value pairs, where each key is unique and has a value associated with that key. You should sort the list of dictionaries from smallest to largest by their 'first' key. If there is two dictionaries with the same 'first' value then sort them by their 'second' key. Negative numbers should come before positive numbers.
--------
Question: [{'first': 89, 'second': -45}, {'first': 17, 'second': -35}, {'first': -74, 'second': -21}, {'first': 58, 'second': 10}]
Answer: [{'first': -74, 'second': -21}, {'first': 17, 'second': -35}, {'first': 58, 'second': 10}, {'first': 89, 'second': -45}]
Question: [{'first': 93, 'second': -31}, {'first': 52, 'second': 7}, {'first': -32, 'second': 54}, {'first': 52, 'second': 83}, {'first': 92, 'second': -31}, {'first': 9, 'second': -47}, {'first': 69, 'second': 48}]
Answer: [{'first': -32, 'second': 54}, {'first': 9, 'second': -47}, {'first': 52, 'second': 7}, {'first': 52, 'second': 83}, {'first': 69, 'second': 48}, {'first': 92, 'second': -31}, {'first': 93, 'second': -31}]
Question: [{'first': 18, 'second': -55}, {'first': 98, 'second': -83}, {'first': 6, 'second': -11}]
Answer: | [{'first': 6, 'second': -11}, {'first': 18, 'second': -55}, {'first': 98, 'second': -83}]
|
In this task, you are given a list of unique integers you need to swap the positions of maximum and minimum element in the list and return the updated list.
Ex Input:
[424, 356, 298, 311, 433, 419, 23, 69, 27, 499, 108, 140, 190, 442, 196, 383, 445, 93, 20, 490]
Ex Output:
[424, 356, 298, 311, 433, 419, 23, 69, 27, 20, 108, 140, 190, 442, 196, 383, 445, 93, 499, 490]
Ex Input:
[335, 387, 238, 71, 92, 382, 227, 348, 383, 475, 117, 181, 345, 288, 23, 397, 39, 273, 343, 202]
Ex Output:
[335, 387, 238, 71, 92, 382, 227, 348, 383, 23, 117, 181, 345, 288, 475, 397, 39, 273, 343, 202]
Ex Input:
[114, 363, 306, 103, 146, 131, 217, 420, 350, 66, 195, 442, 313, 153, 235, 18, 127, 204, 247, 291]
Ex Output:
| [114, 363, 306, 103, 146, 131, 217, 420, 350, 66, 195, 18, 313, 153, 235, 442, 127, 204, 247, 291]
|
Detailed Instructions: 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.
Problem:Ìtọ́ni náà ṣe kedere nínú Ìwé Òfin (Àpilẹ̀kọ 2, 13 àti 32), Ìpolongo Ẹ̀tọ́ Ọmọnìyàn Lágbàáyé, Àpéjọ Oviedo, àti nínú ìwé òfin Ẹ̀tọ́ Ọmọnìyàn ti Ilẹ̀ Yúróòpù.’ ” —Antonio Corcione, tó jẹ́ olùṣekòkáárí ní ojúkò tí wọ́n ti ń pààrọ̀ ẹ̀yà ara ti agbègbè Campania. Òun ló ń bójú tó ẹ̀ka àwọn tó ń pa ìrora nígbà iṣẹ́ abẹ tó sì ń pèsè ìtọ́jú àkànṣe ní ilé ìwòsàn Monaldi. Ó sì tún fìgbà kan jẹ́ ààrẹ ẹgbẹ́ Italian Society of Anesthesia, Analgesia, Resuscitation, and Intensive Care (SIAARTI). “Ìrírí tí mo ní nígbà tí mo tọ́jú àwọn Ẹlẹ́rìí Jèhófà ti ran èmi àtàwọn dókítà míì títí kan àwọn nọ́ọ̀sì lọ́wọ́, ó ti jẹ́ ká ṣàtúnṣe sí ọ̀nà tá à ń gbà ṣiṣẹ́ abẹ kí ẹ̀jẹ̀ tó máa dànù lè dín kù gan-an. Nípa bẹ́ẹ̀, aláìsan náà ò ní nílò ìfàjẹ̀sínilára.
Solution: | The document makes it explicit that ‘the right of self-determination in relation to health care is a fundamental right of the person guaranteed by the Constitution (Articles 2, 13, and 32), the Universal Declaration of Human Rights, the Oviedo Convention, and the Charter of Fundamental Rights of the European Union.’”—Antonio Corcione, coordinator of the regional transplant center for the Campania region, director of anesthesia and intensive care units at the Monaldi Hospital, former president of the Italian Society of Anesthesia, Analgesia, Resuscitation, and Intensive Care (SIAARTI) “My experience with Jehovah’s Witnesses motivated me and all my colleagues to refine blood-saving and postoperative management techniques in order to limit the need for transfusion support. |
Given the task definition and input, reply with output. 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.
Prompt: Let me sign this contract!! I'm the Chief Executive Officer of
Completion A: the company and I have to do it for myself. If you see me in a place where my rights are violated you know what I'm talking about
Completion B: the world's largest and most innovative technology company. You can see me on the Internet. Please do not ask me for my number from here,
| Completion B |
Detailed Instructions: You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Galician.
Q: فكل تجربة يمكن أخذها على حدى.
A: | Todas as experiencias son únicas. |
Detailed Instructions: In this task, we have Spanish and Catalan tweets for automatic stance detection. The data has three labels Against, Favor, and Neutral which express the stance towards the target -independence of Catalonia. If the tweet criticizes the independence of Catalonia then it's 'Against' and if the tweets support it then it will be labeled as 'Favor' also if the tweets state information or news rather than stating opinion then it will be characterized as 'Neutral'.
Q: Tweet: @barrugat @pilarcarracelas @KhommonNoise @voluntatdeser Defensar la seva Constitució, les lleis de tots, el seu territori i la seva població. Res mès. El titol sería: cap país democrátic soportaría aquesta mena de boixeria separatista amb tanta paciència.
A: | Against |
Part 1. Definition
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.
Part 2. Example
19:00 Hrs
Answer: 07:00 PM
Explanation: For a 24-Hours format time larger than 12:00, we should subtract 12 hours from the given time, then add 'PM'. So, the output is correct.
Part 3. Exercise
04:11 Hrs
Answer: | 04:11 AM |
Detailed Instructions: 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.
Problem:New Zealand
Solution: | .nz |
Instructions: Given the following Catalan sentence, indicate the name entities (i.e., the real-world objects such as a person, location, organization, etc. that can be denoted with a proper name) such as 'New York Times'. For each words of a named-entity, indicate their type 'LOC' or 'ORG' or 'PER', where 'LOC' indicates a location entity (such as 'New York City', 'ORG' indicates the token of an organization (such as 'Amazon'), 'PER' indicates the tokens of a person entity (such as 'Jeff Bezos'). Named entities with other types should be indicated with 'MISC'. To indicate boundaries of an entity, use IOB (Inside-Output-Begin) prefixes. The B- prefix before a tag indicates that the word is the beginning of a named entity. The I- prefix indicates that the word is inside a bigger chunk. For example, you can break 'New York' to 'New' and 'York.' and tag them as 'B-LOC' and 'I-LOC'. Any token that doesn't belong to a named entity must be tagged with 'O'.
Input: Esquerra Republicana de Catalunya ( ERC ) es proposa dur el Pla Hidrològic Nacional ( PHN ) al Consell Consultiu de la Generalitat perquè estudiï si és constitucional .
Output: | Esquerra (B-ORG) Republicana (I-ORG) de (I-ORG) Catalunya (I-ORG) ( (O) ERC (B-ORG) ) (O) es (O) proposa (O) dur (O) el (O) Pla (B-MISC) Hidrològic (I-MISC) Nacional (I-MISC) ( (O) PHN (B-MISC) ) (O) al (O) Consell (B-ORG) Consultiu (I-ORG) de (I-ORG) la (I-ORG) Generalitat (I-ORG) perquè (O) estudiï (O) si (O) és (O) constitucional (O) . (O) |
Detailed Instructions: 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_LOOK
A: | look after run right twice |
In this task, you will be given a list of numbers. The goal is to divide all the numbers in the list by a constant such that the sum of the resulting list is 1. The output should be rounded to 3 decimals.
[212.488, 173.438, -88.544, 152.526, -21.513, -68.928] | [ 0.591 0.482 -0.246 0.424 -0.06 -0.192] |
In this task you're given two statements in Marathi. You must judge whether the second sentence is the cause or effect of the first one. The sentences are separated by a newline character. Output either the word 'cause' or 'effect' .
--------
Question: त्या माणसाने चित्रकलेचा विचार केला.
त्याला आश्चर्य वाटले.
Answer: effect
Question: महिलेला ज्यूरी ड्युटीसाठी बोलावले होते.
तिने आपल्या भेटी रद्द केल्या.
Answer: effect
Question: शहराने पुन्हा महापौरपदी निवड केली.
महापौरांनी आपली आश्वासने पूर्ण केली.
Answer: | cause
|
Given the task definition and input, reply with output. 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
[193, 184, 175, 166, 157, 148, 139, 130, 121, 112, 103, 94, 85, 76, 67, 58, 49, 40, 31, 22]
| 1 |
In this task, you will be given a sentence or two along with a change aspect. You should change the given text in the given aspect. Aspects are explained below:
Tense: Change the tense of the verbs in the text. If they're in past tense, change them to present, and if they're in present tense, change them to past tense.
Number: Change the number of the nouns in the given text. Make plurals into singles and single into plurals. Remember to change the corresponding pronouns accordingly.
Voice: If the verbs are in active voice, change them to be passive, otherwise, change them to be in active voice.
Adverb: add one or multiple adverbs to the text.
Gender: If the text contains female names and pronouns, substitute them with male names and pronouns. Do the same for sentences with mala names and pronouns.
[EX Q]: sentence: Since it was raining , I carried the newspaper in my backpack to keep it dry . aspect: Tense
[EX A]: Since it is raining , I am carrying the newspaper in my backpack to keep it dry .
[EX Q]: sentence: The painting in Mark's living room shows an oak tree . it is to the right of the bookcase . aspect: Voice
[EX A]: An oak tree is shown in the painting in Mark's living room . it is to the right of the bookcase .
[EX Q]: sentence: The foxes are getting in at night and attacking the chickens . I shall have to kill them . aspect: Adverb
[EX A]: | The foxes are slyly getting in at night and fiercly attacking the chickens . I shall certainly have to kill them .
|
Definition: In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.
Input: threetwofivetwosevenfivezerosevenzeroeightseven
Output: | 32527507087 |
Detailed Instructions: In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.
Q: fourfoursixeightninetwoonesixonezeronineeight
A: | 446892161098 |
Detailed Instructions: 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.
Problem:Prompt: Fuck you, 50, you're an old person going to a matinee.
Completion A: Dumbass! He's my enemy because of the way he looks at me. How dare you. You're not supposed to date a
Completion B: A matinee is held after a performance, a performance before a movie. A matinee allows people to sit back and watch th
Solution: | Completion B |
We would like you to assess the QUALITY of each of the following argument (discussing Gay Marriage) 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 gay marriage. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of gay marriage.
--------
Question: Yes you are because you believe it is a sin and want to stop two men from getting married doesn't mean everyone believes it is a sin.
Answer: Valid
Question: If you consider sexual deviancy as normal then you can consider gay sex as normal.
Answer: Valid
Question: Unlike many conservatives who, for example, are trying to pretend that judges don't have the right to rule on matters of law.
Answer: | Invalid
|
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 a country name, and you need to return the year in which the country became independent. Independence is a nation's independence or statehood, usually after ceasing to be a group or part of another nation or state, or more rarely after the end of military occupation.
Angola
Solution: 1975
Why? 1975 is the year of independence of Angola.
New input: China
Solution: | -1523 |
Detailed Instructions: In this task you are expected to write an SQL query that will return the data asked for in the question. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the "SELECT" statement. Next, you use a "FROM" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the "AS" statement. You can reference that table by whatever name follows the "AS" statement. If you want to select data from multiple tables you need to use the "JOIN" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the "ON" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the "WHERE" statement to specify that only rows with column values statisfying a certain condition, should be returned. The "GROUP BY" statement will group rows together that have equal column values for whatever columns follows the statement. The "HAVING" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the "ORDER BY" command which will order the data by whatever aggregate function or column follows the statement. The "DESC" statement will sort in descending order and the "ASC" statement will sort in ascending order. Finally, you can use the "LIMIT" statement to return a certain number of rows. When "*" is used in an SQL statement every column is returned. For example, SELECT * FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.
Q: What are the names of entrepreneurs and their corresponding investors, ordered descending by the amount of money requested?
A: | SELECT T2.Name , T1.Company FROM entrepreneur AS T1 JOIN people AS T2 ON T1.People_ID = T2.People_ID ORDER BY T1.Money_Requested |
In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.
One example: twotwoonesixzeronine
Solution is here: 221609
Explanation: The string is properly converted into a number based on the spelling of each digit. The string started with 'twotwo' therefore the number also started with '22'. This is a good example.
Now, solve this: fivefourninetwosevennineninefivesixsevenseven
Solution: | 54927995677 |
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.
Ex Input:
eq { count { filter_eq { filter_eq { all_rows ; builder ; general dynamics , quincy } ; commissioned - decommissioned ; 1969 } } ; 2 }
Ex Output:
count
Ex Input:
eq { hop { argmax { filter_eq { all_rows ; team ; ulrich } ; year } ; start } ; 33 }
Ex Output:
superlative
Ex Input:
round_eq { sum { all_rows ; payout ( us ) } ; 16,030,000 }
Ex Output:
| aggregation
|
Detailed Instructions: 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.
See one example below:
Problem: Review: I stayed at the Hilton Chicago for my cousins wedding. The service was impeccable. Not only was the staff attentive, they were respectful and careful not to interrupt the guests or make themselves known when serving dinner. I had the chicken wellington and it was to die for! The chicken was perfect and moist but the pastry crust was flaky and crispy. They even had Pakistani dinner options for some of the guests. The amenities were great, and after an open bar the night before, the Mimosas and brunch buffet couldn't have been better! I would love to have my wedding there.
Polarity: Positive
Solution: true
Explanation: Review writer likes the hotel. There are strong positive words like 'impeccable' and 'great'. Therefore it is true as the polarity mentioned.
Problem: Review: My stay at the Fairmont Chicago Millennium Park Hotel was by far the worst hotel stay I ever had. I would not recommend this hotel to anyone. They promised I would be able to relax in the spa area and it was dirty and not relaxing at all. When I got to my room I ordered room service and it took them 45 minutes to bring what I ordered. I am highly dissatisfied.
Polarity: Positive
Solution: | false |
In this task, you are given a date in "mm/dd/yyyy" format. You need to check if the date is valid or not. Return 1 if it is valid, else return 0. A date is valid is the components month("mm"), day("dd") and year("yyyy") are all valid individually. A day(dd) is valid if it is greater than or equal to 1 and less than 30 or 31 depending upon the month(mm). Months which have 31 days are January, March, May, July, August, October, December. Rest of the months have 30 days except February which has 28 days if it is not a leap year and 29 days if it is a leap year. A month(mm) is valid if it lies in the range from 1 to 12 as there are 12 months in a year. A year is always valid if it is expressed in the form of "yyyy".
Q: 16/29/1206
A: | 0 |
Instructions: The given sentence contains a typo which could be one of the following four types: (1) swapped letters of a word e.g. 'niec' is a typo of the word 'nice'. (2) missing letter in a word e.g. 'nic' is a typo of the word 'nice'. (3) extra letter in a word e.g. 'nicce' is a typo of the word 'nice'. (4) replaced letter in a word e.g 'nicr' is a typo of the word 'nice'. You need to identify the typo in the given sentence. To do this, answer with the word containing the typo.
Input: a cat is sitting in a packed fridgre
Output: | fridgre |
In this task, you will be presented with a question in Dutch language, and you have to write the person names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Phrase used for the person name - PER. There can be instances with no person name entity, then return 'None'.
Ik heb ook het scoringspercentage van de gemiddelde Nederlandse voetballer vanop elf meter onderzocht .
None
" Ach , we moeten hen tijd geven , het zal allemaal wel voorbijgaan .
None
Natuurlijk zijn er ook vrouwen die even voetbalgek zijn als hun mannelijke partners , geeft Vandamme toe , die de VOC-oprispingen over voetbal als " ludiek " bestempelt .
| Vandamme: B-PER
|
Find the movie name from the given conversation. If the movie name is not found give output as "unknown"
Input: Consider Input: ASSISTANT: What kind of movies do you not like? , USER: I don't like horror movies, and I don't like drama movies. , ASSISTANT: Why do you not like Horror movies? , USER: I find they're often too predictable and too cliche. Usually, the plots are really similar which is that there is something scary, nobody knows about it, but it's killing people or terrorizing people or something. And then they figure it and they usually they end up beating it or locking it away or whatever it is that ends up happening to it. , ASSISTANT: What kind of movies do you like the most? , USER: It's a toss-up between comedy and war movies. , ASSISTANT: What was the last movie that you watched that disappointed you , USER: Deadpool
Output: Deadpool
Input: Consider Input: ASSISTANT: What type of movies do you like? , USER: I really like action movies. , ASSISTANT: Why do you like those movies? , USER: I like the I like the action in them. I like the nonstop sort of rhythm to the movie. It sort of takes you out of reality, really immerses you into the movie. They usually are a lot of fun, although I do prefer the ones that aren't quite so violent, but in general, it's really a nice escape and a lot of fun. , ASSISTANT: What movie specifically do you like? , USER: My favorite is probably Bourne Ultimatum.
Output: Bourne Ultimatum
Input: Consider Input: ASSISTANT: what kind of movies do u like to watch , USER: I typically like Sci-Fi movies. , ASSISTANT: why is that , USER: They typically have imaginative storylines, and fantastical graphics, and things like that. , ASSISTANT: can you name a specific movie that you like that fits that category, and what aspects you like about the movie type , USER: I recently re watched The Matrix and it held up really well. It has a pretty decent plot, the production value there are outstanding and it just looks really good for a movie from the 2000s.
| Output: The Matrix
|
In this task, you will be shown an English sentence. You need to classify the sentence as either a representation of an anaphor number agreement or as an incorrect representation. An anaphor is an expression whose interpretation depends upon another expression. Anaphor number agreement is a restriction where a phrase agrees with the preceeding expression: plurals match plurals or singular expressions match singular expressions. In this task a valid representation of anaphor number agreement should be denoted as 'good' while everything else should be denoted as 'bad'. A correct representation of an anaphor number agreement will be a grammatically correct instance of a sentence where the subject and self-referencing nouns match plurality. An incorrect representation is a sentence in which the subject and self-referencing noun's plurality do not match.
Q: Lisa couldn't flee from herself.
A: | good |
TASK DEFINITION: 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
PROBLEM: [176, 171, 166, 161, 156, 151, 146, 141, 136, 131, 126, 121, 116, 111, 106, 101, 96, 91, 86, 81, 76, 71, 66, 61, 56, 51, 46]
SOLUTION: 1
PROBLEM: [41, 10, 1, 63, 24, 69, 71, 43, 37, 50]
SOLUTION: 2
PROBLEM: [27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128]
SOLUTION: | 1
|
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.
Example Input: Sentence: Finally , {{ from }} an email , a follow - up on the reopening of the investigation into the Atlanta Child Murders :
Word: from
Example Output: IN
Example Input: Sentence: {{ What }} do you like to do ?
Word: What
Example Output: WP
Example Input: Sentence: Beth has made our reservations for the Round Table Friday night {{ ( }} 5/18 ) at Sullivan 's Steak House for 6:30 .
Word: (
Example Output: | -LRB-
|
In this task, you are given a string with duplicate characters ocurring in the string. You need to return the character which is ocurring with the maximum frequency. In case of a tie, return the character with the least ascii value.
iufxlomsgolnpdgeqbpwuvedwdfcgwqkebmfgzlanjmc | g |
In this task, you will be presented with a question in Dutch language, and you have to write the person names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Phrase used for the person name - PER. There can be instances with no person name entity, then return 'None'.
Q: Agassi volgt slechte voorbeeld van de Belgen
A: | Agassi: B-PER |
TASK DEFINITION: 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
PROBLEM: [32, 35, 38, 41, 44, 47, 50, 53, 56, 59, 62, 65, 68, 71, 74, 77, 80, 83, 86, 89, 92, 95, 98, 101]
SOLUTION: 1
PROBLEM: [70, 74, 90, 85, 92, 3, 63, 57, 53, 91]
SOLUTION: 2
PROBLEM: [33, 43, 53, 63, 73, 83, 93, 103, 113, 123, 133, 143, 153, 163]
SOLUTION: | 1
|
In this task, you are given the name of an Indian food dish. You need to return whether the dish is "non vegetarian" or "vegetarian". Do not answer with any words other than those two.
Input: Consider Input: Chicken Tikka masala
Output: non vegetarian
Input: Consider Input: Alu Pitika
Output: non vegetarian
Input: Consider Input: Alu Pitika
| Output: non vegetarian
|
In this task, you are given an english sentence and a kurdish sentence you have to determine if they both are faithful translations of each other.
Construct an answer that is 'Yes' if the second 'Kurdish' sentence is a translation of 'English' sentence and 'No' otherwise
[EX Q]: 'English : “Our fellow carrying out the duty of transferring an explosive substance-laden truck in Amed region to another location was tried to be obstructed by some local collaborative elements in Dürümlü hamlet of Sarıkamış village in Sur district of Amed on May 12”.','Kurdish : ‘Li herêma Amedê, hevalên me qemyonek bi madeyên teqemeniyê barkirî ji cihekî dibir cihekî din. Di êvara 12ê Gulanê de me li gundikê Durumlu yê gundê Sarikamiş ê li navçeya Amed Sûrê dema di rê de bû, hin nokeran hewl dan pêşî lê bigirin. Hevalê di qemyonê de wezîfedar, nasnameya xwe eşkere kir û jê re nebin asteng û xwest biçe.’'
[EX A]: Yes
[EX Q]: 'English : “At that moment, they stopped me in the airport and said they needed to check some things. I waited in the airport for around 2-3 hours.','Kurdish : ‘’Ez dibêjim qey hingê biryar dan ku min desteser bike, Paşê wan ez birim Navenda Polîsan a Caddeya Vatanê.'
[EX A]: No
[EX Q]: 'English : According to bianet’s Media Monitoring Report covering the months of January, February, March the number of arrested journalists was 28. With the arrest of eight other journalists since April, the number has reached 36.','Kurdish : Di Rapora Çavdêriya li Medyayê ya Çile-Sibat-Adarê ku ji hêla bianetê ve hat amadekirin de hejmara rojnamegerên girtî 28 bû. Ji meha Nîsanê vir ve 8 rojnamegerên din jî hatin girtin û hejmar gihişte 36an.'
[EX A]: | Yes
|
Q: Two analogies that relate objects to the associated rooms is given in the form "A : B. C : ?". "A : B" relates object A to room B. Your task is to replace the question mark (?) with the appropriate room for the given object C, following the "A : B" relation.
workbench : workshop. recliner : ?
A: | den |
Q: 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.
password = ztJQJ
A: | 1 |
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.
Q: [35, -72, 95, 14, -61, 90, 17]
A: | 3 |
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: Ooh, this didn't age well
A: | no |
Detailed Instructions: The provided text is in English, and we ask you to translate the text to the Croatian language. Please bear in mind the following guidelines while translating: 1) We want a natural translation, a formal form. 2) Use the symbols like '#@%$-+_=^&!*' as-is. *Include* the special characters as suited when translating to Croatian. 3) Quantities like millions or billions should be translated to their equivalent in Croatian language 4) Note the input is all case-sensitive except for special placeholders and output is expected to be case-sensitive. 5) The output must have Croatian characters like Ž or č and the output must preserve the Croatian language characters. 6) The input contains punctuations and output is expected to have relevant punctuations for grammatical accuracy.
Q: It's quite a familiar story.
A: | To je prilično poznata priča. |
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.
One example: [-11, 2, 3]
Solution is here: -11
Explanation: The element with the largest absolute value is -11, since 11 > 3 > 2. This is a good example.
Now, solve this: [ 59.829 35.416 94.083 -99.799 -94.438 55.02 -6.595]
Solution: | -99.799 |
This task is to find the number of 'For' loops present in the given cpp program.
int s=0;
void f(int x,int y)
{
int i,j,k;
if(x==1)
s++;
else
{
for(;y<=x;y++)
{
if(x%y==0)
{
f(x/y,y);
}
}
}
}
int main()
{
int n,k,q,j;
scanf("%d",&q);
for(j=0;j<q;j++)
{
scanf("%d",&n);
f(n,2);
printf("%d\n",s);
s=0;
}
return 0;
} | 2 |
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 = zuo4t
A: | 1 |
Part 1. Definition
In this task you will be given two lists of numbers and you need to calculate the intersection between these two lists. The intersection between two lists is another list where every element is common between the two original lists. If there are no elements in the intersection, answer with an empty list. Your list of numbers must be inside brackets. Sort the numbers in your answer in an ascending order, that is, no matter what the order of the numbers in the lists is, you should put them in your answer in an ascending order.
Part 2. Example
[2,5,1,4],[2,5,8,4,2,0]
Answer: [2,4,5]
Explanation: The elements 2,4, and 5 are in both lists. This is a good example.
Part 3. Exercise
[8, 3, 5, 10, 9, 4, 10, 3] , [2, 5, 7, 6, 10, 9, 9, 5]
Answer: | [5, 9, 10] |
Given an adjective, generate its antonym. An antonym of a word is a word opposite in meaning to it.
sure | unsure |
instruction:
The provided file includes inquiries about restaurants in Spanish, and we ask you to translate those to English 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.
question:
dígame cuál es la valoración del "wendy 's".
answer:
tell me the rating of " wendy 's " .
question:
¿cuál es el restaurante más cercano a mí?
answer:
what is the closest restaurant to me ?
question:
muestra restaurantes de " san francisco " .
answer:
| show restaurants in " san francisco " .
|
Detailed Instructions: In this task, you are given two strings A,B. You must perform the following operations to generate the required output list: (i) Find the longest common substring in the strings A and B, (ii) Convert this substring to all lowercase and sort it alphabetically, (iii) Replace the substring at its respective positions in the two lists with the updated substring.
Q: gUqhIbkeYinRLRIrIazXoZet, IJrCIywkeYinRLRIrIatqdasjU
A: | gUqhIbaeiiiklnrrryzXoZet, IJrCIywaeiiiklnrrrytqdasjU |
In this task, you need to output 'Yes' if the given number is a prime number otherwise output 'No'. A 'prime number' is a a whole number above 1 that can not be made by multiplying other whole numbers.
Q: 1163
A: | Yes |
Definition: In this task, you're given a sentence and question. Based on the information provided in a given sentence, you should identify the shortest continuous text span from the sentence that serves as an answer to the given question. Answer the question using coreference resolution. Coreference resolution is the task of clustering mentions in text that refer to the same underlying real world entities. For example let's take a sentence 'I voted for Obama because he was most aligned with my values, she said.' Here in this example 'I', 'my', and 'she' belong to the same cluster and 'Obama' and 'he' belong to the same cluster. Now let's discuss another example , original sentence: 'I voted for Trump because he was most aligned with my values',John said. Now here is the same sentence with resolved coreferences: 'John voted for Trump because Trump was most aligned with John's values',John said.
Input: Sentence: Everyone really loved the oatmeal cookies; only a few people liked the snickerdoodle cookies. Next time, we should make fewer of them. Question: Which cookie should we make fewer of, next time?
Output: | snickerdoodle |
Given the task definition and input, reply with output. In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.
twofoureightthreeonefiveninetwotwosixnine
| 24831592269 |
Part 1. Definition
Given a pair of words, generate the relation between them. The first word is called the 'concept' and the second word is called the 'relatum' The relation must be one of the following: co-hyponym (coordinate), hypernym, meronym, attribute, event, or random. A coordinate relation indicates that the concept and relatum belong to the same semantic class. A hypernym relation indicates that the relatum is a category of which the concept is a specific instance. A meronym relation implies that relatum is a part/component/organ/member of the concept. An attribute relation is when the relatum is an adjective expressing an attribute of the concept. An event relation holds when the relatum is a verb referring to an action/activity/happening/event that is performed by or with the concept. If the relatum and concept are unrelated, the relation between them is 'random'. Classify your answers into coord, hyper, mero, attri, event, and random.
Part 2. Example
Concept: alligator, Relatum: lizard.
Answer: coord
Explanation: Alligator and lizard belong to the same semantic class of reptiles, so the relation is coordinate.
Part 3. Exercise
Concept: alligator, Relatum: leg.
Answer: | mero |
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].
Example input: question: What are the distinct creation years of the departments managed by a secretary born in state 'Alabama'?
Example output: #1 return secretaries
#2 return #1 born in state 'Alabama
#3 return departments managed by #2
#4 return distinct creation years of #3
Example explanation: Referring to previous steps is vital in constructing multi-step decompositions. In this example each step refers to the step before to perform a single filter on it to reach the final result.
Q: question: If the marmots are all a similar color.
A: | #1 return marmots
#2 return colors of #1
#3 return if #2 are all similar |
Given the task definition and input, reply with output. In this task you will be given a list of numbers and you should remove all duplicates in the list. If every number is repeated in the list an empty list should be returned. Your list should be numbers inside brackets, just like the given list.
[0, 2, 7, 3, 1, 4, 5]
| [0, 2, 7, 3, 1, 4, 5] |
Q: In this task, you will be shown a sentence, and you should determine whether it is overruling or non-overruling. In law, an overruling sentence is a statement that nullifies a previous case decision as a precedent by a constitutionally valid statute or a decision by the same or higher ranking court which establishes a different rule on the point of law involved. Classify your answers into overruling or non-overruling
( 4056, subd. (a)(3).)
A: | non-overruling |
Part 1. Definition
In this task, you are given a year. You need to check if it is a leap year or not. A year may be a leap year if it is evenly divisible by 4. Years that are divisible by 100 (century years such as 1900 or 2000) cannot be leap years unless they are also divisible by 400. Return 1 if it is a leap year, else return 0.
Part 2. Example
1644
Answer: 1
Explanation: 1644 is a leap year as 1644 is divisible by 4.
Part 3. Exercise
1844
Answer: | 1 |
For the given English description, write an SQL command such that it accomplishes every step. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the "SELECT" statement. Next, you use a "FROM" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the "AS" statement. You can reference that table by whatever name follows the "AS" statement. If you want to select data from multiple tables you need to use the "JOIN" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the "ON" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the "WHERE" statement to specify that only rows with column values statisfying a certain condition, should be returned. The "GROUP BY" statement will group rows together that have equal column values for whatever columns follows the statement. The "HAVING" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the "ORDER BY" command which will order the data by whatever aggregate function or column follows the statement. The "DESC" statement will sort in descending order and the "ASC" statement will sort in ascending order. Finally, you can use the "LIMIT" statement to return a certain number of rows. When "*" is used in an SQL statement every column is returned. For example, SELECT * FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.
Ex Input:
Did M0 influence M1 , influence M2 , M3 , and M4 , and influence M5 , M6 , and M7
Ex Output:
SELECT count(*) WHERE {
M0 ns:influence.influence_node.influenced M1 .
M0 ns:influence.influence_node.influenced M2 .
M0 ns:influence.influence_node.influenced M3 .
M0 ns:influence.influence_node.influenced M4 .
M0 ns:influence.influence_node.influenced M5 .
M0 ns:influence.influence_node.influenced M6 .
M0 ns:influence.influence_node.influenced M7
}
Ex Input:
Did M0 's executive producer , cinematographer , editor , writer , and star executive produce and produce M1
Ex Output:
SELECT count(*) WHERE {
?x0 ns:film.actor.film/ns:film.performance.film M0 .
?x0 ns:film.cinematographer.film M0 .
?x0 ns:film.editor.film M0 .
?x0 ns:film.producer.films_executive_produced M0 .
?x0 ns:film.producer.films_executive_produced M1 .
?x0 ns:film.producer.film|ns:film.production_company.films M1 .
?x0 ns:film.writer.film M0
}
Ex Input:
Did M7 's French Japanese female spouse play M2 , M3 , and M4 and play M5
Ex Output:
| SELECT count(*) WHERE {
?x0 ns:film.actor.film/ns:film.performance.character M2 .
?x0 ns:film.actor.film/ns:film.performance.character M3 .
?x0 ns:film.actor.film/ns:film.performance.character M4 .
?x0 ns:film.actor.film/ns:film.performance.character M5 .
?x0 ns:people.person.gender ns:m.02zsn .
?x0 ns:people.person.nationality ns:m.03_3d .
?x0 ns:people.person.nationality ns:m.0f8l9c .
?x0 ns:people.person.spouse_s/ns:people.marriage.spouse|ns:fictional_universe.fictional_character.married_to/ns:fictional_universe.marriage_of_fictional_characters.spouses M7 .
FILTER ( ?x0 != M7 )
}
|
In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.
Sentence: 'a blue snowboad with some writing on the top of it'. Is 'the' the longest word in the sentence?
No
Sentence: 'a girl is playing with a frisbee outside by a house'. Is 'outside' the longest word in the sentence?
Yes
Sentence: 'a man reaching up to grab a frisbee on the beach'. Is 'man' the longest word in the sentence?
| No
|
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
We would like you to assess the QUALITY of each of the following argument (discussing Gay Marriage) 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 gay marriage. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of gay marriage.
It is usually just as religiously important to same-sex couples to be married as it is for opposite-sex couples, and no one should be able to tell those people that the government cannot recognize their relationship.
Solution: Valid
Why? It is a clear argument that supports gay marriage by saying it is as religiously important as opposite-sex marriage.
New input: And some people, who happen to dislike gay people, should not be allowed to use the state to aim discriminatory laws against gay people.
Solution: | Valid |
You will be given a definition of a task first, then some input of the task.
Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.
11:15:45 occured after 3:22:41 PM but before 8:43:19
Output: | False |
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.
Q: Juventus yóò máa kojú ikọ̀ agbábọ́ọ̀lù AC Milan lọ́jọ́ kọkànlélọ́gbọ̀n (31) oṣù kẹ̀ta, bẹ́ẹ̀ sì ni wọn yóò tún lọ gbá ìfẹsẹ̀wọnsẹ̀ àkọ́kọ́ ìdíje UEFA Champions League pẹ̀lú Real Madrid lọ́jọ́ kẹta inú oṣù kẹ̀rin.
A: | Juve’s next match is against AC Milan on March 31, followed by the first leg of their UEFA Champions League quarter-final against Real Madrid on April 3. |
Detailed Instructions: In this task, you will be given a sentence or two along with a change aspect. You should change the given text in the given aspect. Aspects are explained below:
Tense: Change the tense of the verbs in the text. If they're in past tense, change them to present, and if they're in present tense, change them to past tense.
Number: Change the number of the nouns in the given text. Make plurals into singles and single into plurals. Remember to change the corresponding pronouns accordingly.
Voice: If the verbs are in active voice, change them to be passive, otherwise, change them to be in active voice.
Adverb: add one or multiple adverbs to the text.
Gender: If the text contains female names and pronouns, substitute them with male names and pronouns. Do the same for sentences with mala names and pronouns.
Problem:sentence: Jane knocked on Susan's door , but there was no answer . She was out . aspect: Adverb
Solution: | Jane repeatedly knocked on Susan's door , but there was no answer . She really was out . |
You will be given a definition of a task first, then some input of the task.
Indicate if the following Polish tweet contains cyber-bullying content with 'Yes'; otherwise, respond with 'No'.
Tweet: @anonymized_account @anonymized_account Dobrze że w bierkach nie są mistrzem bo wtedy byłoby pozamiatane , Question: Does the tweet contain cyberbullying (harmful) content?
Output: | No |
Two analogies that relate objects to the associated rooms is given in the form "A : B. C : ?". "A : B" relates object A to room B. Your task is to replace the question mark (?) with the appropriate room for the given object C, following the "A : B" relation.
boxes : attic. desk : ?
office
recliner : den. cabinet : ?
bathroom
shelf : pantry. couch : ?
| parlor
|
Definition: In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.
Input: foursevenfiveonezerotwosevensixninefour
Output: | 4751027694 |
End of preview. Expand
in Dataset Viewer.
- Downloads last month
- 44
Size of downloaded dataset files:
170 MB
Size of the auto-converted Parquet files:
170 MB
Number of rows:
202,695