inputs
stringlengths
23
351k
targets
stringlengths
0
27.3k
_template_idx
int64
0
17
_task_source
stringclasses
4 values
_task_name
stringlengths
8
85
_template_type
stringclasses
2 values
messages
listlengths
2
2
You will be given a definition of a task first, then some input of the task. A text is given in Malayalam. Translate it from the Malayalam language to the Panjabi language. The translation must not omit or add information to the original sentence. -അറിവും വിവരങ്ങളും പങ്കുവയ്ക്കുന്നതിനായി പരിശീലകരെ കൈമാറ്റംചെയ്യുക. Output:
ਗਿਆਨ ਅਤੇ ਜਾਣਕਾਰੀ ਸਾਂਝੇ ਕਰਨ ਲਈ ਟ੍ਰੇਨਰਾਂ ਦਾ ਅਦਾਨ-ਪ੍ਰਦਾਨ ਕਰਨਾ।
1
NIv2
task1005_pib_translation_malayalam_punjabi
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nA text is given in Malayalam. Translate it from the Malayalam language to the Panjabi language. The translation must not omit or add information to the original sentence.\n\n-അറിവും വിവരങ്ങളും പങ്കുവയ്ക്കുന്നതിനായി പരിശീ...
Teacher:Given a premise and two alternatives in Gujarati, choose the alternative that is either a plausible cause or effect of the situation described by the premise. The premise is the 'નિવેદન' field and the alternatives are the 'વિકલ્પA' and 'વિકલ્પB' fields.The output should either be "વિકલ્પ A" or "વિકલ્પ B" based on your judgment. Teacher: Now, understand the problem? Solve this instance: નિવેદન: સ્ત્રી ડ doctorક્ટર બનવા માંગતી હતી. વિકલ્પ A: તેણીએ હોસ્પિટલની મુલાકાત લીધી હતી. વિકલ્પ B: તે મેડિકલ સ્કૂલ ગઈ હતી. Student:
વિકલ્પ B
6
NIv2
task940_copa_gu_commonsense_reasoning
zs_opt
[ { "content": "Teacher:Given a premise and two alternatives in Gujarati, choose the alternative that is either a plausible cause or effect of the situation described by the premise. The premise is the 'નિવેદન' field and the alternatives are the 'વિકલ્પA' and 'વિકલ્પB' fields.The output should either be \"વિકલ્પ ...
Detailed Instructions: A text is given in Marathi. Translate it from the Marathi language to the Urdu language. The translation must not omit or add information to the original sentence. Problem:मी तुम्हा सर्वांना समाधानकारक आणि सर्जनशील नवीन वर्षाची शुभेच्छा देतो. Solution:
میری دعا ہے کہ نئے سال میں آپ کی آرزوؤں اور آپ کی تخلیقی صلاحیتوں کی تکمیل ہو۔
8
NIv2
task989_pib_translation_marathi_urdu
zs_opt
[ { "content": "Detailed Instructions: A text is given in Marathi. Translate it from the Marathi language to the Urdu language. The translation must not omit or add information to the original sentence.\nProblem:मी तुम्हा सर्वांना समाधानकारक आणि सर्जनशील नवीन वर्षाची शुभेच्छा देतो.\nSolution:", "role": "user"...
Given the task definition and input, reply with output. In this task, you will be given a short story. One sentence from the story is chosen. Consider the events that happen after that sentence. Is any of them directly caused by it, or is made possible by it? You should write your answer in the form " A >causes/enables> B". Try to use phrases and sentences from the story to compose your answer when possible. Do not change the main selected sentence in your answer. story: It was very windy and rainy outside. Ava took her umbrella with her when she left. But as she walked, the wind increased. The umbrella was ripped from her hands and carried away! Poor Ava had to walk with no umbrella. selected sentence: The umbrella was ripped from her hands and carried away!
Ava's umbrella is ripped from her hands >Causes/Enables> Ava watches the umbrella
5
NIv2
task748_glucose_reverse_cause_event_detection
zs_opt
[ { "content": "Given the task definition and input, reply with output. In this task, you will be given a short story. One sentence from the story is chosen. Consider the events that happen after that sentence. Is any of them directly caused by it, or is made possible by it? You should write your answer in the fo...
Teacher:The task is to generate the correct answer for a given math problem. Teacher: Now, understand the problem? Solve this instance: Problem: aishwarya rai walks into a bank to cash out her check . by mistake the bank teller gives her dollar amount in change , and her cent amount in dollars . on the way home she spends 5 cent , and then suddenly she notices that she has twice the amount of her check . how much was her check amount ? Student:
31.6
6
NIv2
task1726_mathqa_correct_answer_generation
zs_opt
[ { "content": "Teacher:The task is to generate the correct answer for a given math problem.\nTeacher: Now, understand the problem? Solve this instance: Problem: aishwarya rai walks into a bank to cash out her check . by mistake the bank teller gives her dollar amount in change , and her cent amount in dollars . ...
Given the task definition and input, reply with output. You are given a sentence in English. Your job is to translate the English sentence into Arabic. Sequoia sempervirens is the tallest living organism on Earth.
"" سيكويا سيبيرفيرينز "" هي أطول كائن حي على وجه الأرض.
5
NIv2
task1220_ted_translation_en_ar
zs_opt
[ { "content": "Given the task definition and input, reply with output. You are given a sentence in English. Your job is to translate the English sentence into Arabic.\n\nSequoia sempervirens is the tallest living organism on Earth.\n", "role": "user" }, { "content": "\"\" سيكويا سيبيرفيرينز \"\" هي أ...
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. Q: Sentence: 'a zebra grazing in a field eating grass'. Is 'zebra' the longest word in the sentence? A:
No
4
NIv2
task114_is_the_given_word_longest
zs_opt
[ { "content": "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...
Instructions: In this task, you are given an input list A. You need to find all the elements of the list that are numbers and calculate their sum. Input: ['J', '3909', '9609', 'I', 'n', '1595', '4159', '1181', '9847', '9855', 'b', 'o', 'I', 'k', '7759', '7921', '817'] Output:
56652
3
NIv2
task499_extract_and_add_all_numbers_from_list
zs_opt
[ { "content": "Instructions: In this task, you are given an input list A. You need to find all the elements of the list that are numbers and calculate their sum.\nInput: ['J', '3909', '9609', 'I', 'n', '1595', '4159', '1181', '9847', '9855', 'b', 'o', 'I', 'k', '7759', '7921', '817']\nOutput:", "role": "user...
Given the task definition and input, reply with output. Given a sentence in Russian, generate a new Russian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true. Место, где можно бросать еду.
Место, где можно поесть.
5
NIv2
task410_mickey_ru_sentence_perturbation_generation
zs_opt
[ { "content": "Given the task definition and input, reply with output. Given a sentence in Russian, generate a new Russian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have...
Q: A text is given in Bengali. Translate it from the Bengali language to the Marathi language. The translation must not omit or add information to the original sentence. बाजाराशी संलग्न अशा पेट्रोल आणि डिझेलच्या किमतींवर आंतरराष्ट्रीय बाजारातील कच्च्या तेलाच्या किंमतीमधील चढ उतारांचा परिणाम होत असतो. A:
আন্তর্জাতিক ক্ষেত্রে অপরিশোধিত খনিজ তেলের মূল্যের ওপর নির্ভর করে খোলা বাজারের চাহিদা অনুসারে পেট্রেল ও ডিজেলার দাম নির্ধরণ করা হয়েছে।
7
NIv2
task1062_pib_translation_marathi_bengali
zs_opt
[ { "content": "Q: A text is given in Bengali. Translate it from the Bengali language to the Marathi language. The translation must not omit or add information to the original sentence.\nबाजाराशी संलग्न अशा पेट्रोल आणि डिझेलच्या किमतींवर आंतरराष्ट्रीय बाजारातील कच्च्या तेलाच्या किंमतीमधील चढ उतारांचा परिणाम होत अ...
Definition: You are given a statement written in Marathi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option . Input: Statement: कोलार हा <MASK>ाच्या कर्नाटक राज्यामधील एक लोकसभा मतदारसंघ आहे. भारतीय राष्ट्रीय कॉंग्रेस पक्षाचा बालेकिल्ला मानला जाणाऱ्या कोलारमधून वरिष्ठ नेते के.एच. मुनीयप्पा हे १९९१ सालापासून सलग ८ वेळा निवडून आले आहेत. Option A: कर्नाटक Option B: लोकसभा Option C: लष्कर-ए-तोयबा Option D: भारत Output:
भारत
2
NIv2
task950_wiki_cloze_mr_multiple_choice_question_answering
zs_opt
[ { "content": "Definition: You are given a statement written in Marathi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .\nInput: Statement: कोलार हा <MASK>ाच्या कर्नाटक राज्यामधील एक लोकसभा मतदारसंघ आह...
Given the task definition and input, reply with output. Your task is to generate the next utterance in a given dialogue. You will be given a few sentences describing the personality of the person who is making the dialogue, and a history of the dialogue after that. Each line in the history is said by one of the two participants in the conversation. Personality: I hate tomatoes. I need a wheel chair to get around. I'm very short. I'm a female. Chat history: -Hi there, how are you? -Good and thanks for asking. -So tell me about you! You have any kids? -No kids had a car accident. -Oh I am so sorry. I hope I do not ever get in one in my black suburban. -Hope not hard out here finding a man. -I go to 4 book clubs, pta, and 2 brunch groups. Maybe you can come meet someone. -I handicap so is there acess for wheel chairs and I will come. -Sure, and what about girls night.
Well tacos sound fun just no tomatoes and extra salsa please.
5
NIv2
task1729_personachat_generate_next
zs_opt
[ { "content": "Given the task definition and input, reply with output. Your task is to generate the next utterance in a given dialogue. You will be given a few sentences describing the personality of the person who is making the dialogue, and a history of the dialogue after that. Each line in the history is said...
Q: You are given a sentence in Italian. Your job is to translate the Italian sentence into Polish. Fu condannata per il genocidio. A:
Została skazana za zbrodnie ludobójstwa.
7
NIv2
task1253_ted_translation_it_pl
zs_opt
[ { "content": "Q: You are given a sentence in Italian. Your job is to translate the Italian sentence into Polish.\nFu condannata per il genocidio.\nA:", "role": "user" }, { "content": "Została skazana za zbrodnie ludobójstwa.", "role": "assistant" } ]
Teacher:Classify the relation of question with context to one of these categories: 1) award received, 2) based on, collection, 3) conflict, 4) constellation, 5) convicted of, 6) date of death, 7) director, 8) drafted by, 9) educated at, 10) medical condition, 11) military branch, 12) narrative location, 13) occupation, 14) original network, 15) parent company, 16) point in time, 17) production company, 18) residence, 19) series, 20) service entry, 21) sex or gender, 22) spouse, 23) standards body question. Teacher: Now, understand the problem? Solve this instance: Context : Marine Lorphelin (born 16 March 1993) is a French model and beauty queen who was crowned Miss France 2013 on 8 December 2012, representing the region of Burgundy and then represented France at Miss World 2013 and placed 1st runner up. Question : What was the award received by Marine Lorphelin? Student:
award received
6
NIv2
task1328_qa_zre_relation_generation_from_question
zs_opt
[ { "content": "Teacher:Classify the relation of question with context to one of these categories: 1) award received, 2) based on, collection, 3) conflict, 4) constellation, 5) convicted of, 6) date of death, 7) director, 8) drafted by, 9) educated at, 10) medical condition, 11) military branch, 12) narrative loc...
You will be given a definition of a task first, then some input of the task. In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to return the sum of all the numerical elements in the list A between the positions i and j (including positions i and j). Return 0 if no numerical element is present in the list between the given ranges. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j. 2, 6, ['m', 'q', '4069', '4487', 'c', '4639'] Output:
13195
1
NIv2
task606_sum_of_all_numbers_in_list_between_positions_i_and_j
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to return the sum of all the numerical elements in the list A between the positions i and j (including positions i and j...
Instructions: Given a passage classify if the passage has a definite objective/aim/goal or not. Output '1' if the passage has a defininte objective/aim/goal and output '0' if the passage does not have a definite objective/aim/goal. Input: To investigate the associations between the mRNA levels of H19 in term placenta and risk of macrosomia.', 'Term placentas were collected from 37 macrosomia and 37 matched neonates with normal birth weight (controls) born in Changzhou Women and Children Health Hospital, Jiangsu province, P. R. China from March 1 to June 30, 2008. The mRNA levels of H19 in those placentas were measured by real-time polymerase chain reaction (PCR). Simple and multiple logistic regression models were used to explore the risk factors in the development of macrosomia. All analyses were performed using Stata 10.0 (StataCorp, College Station, Texas, USA).', "The average H19 mRNA level of the macrosomia group was 1.450 ±0.456 while in the control group it was 2.080 ±1.296. Based on the result of Student's t test, there was a significant difference in H19 mRNA level between the macrosomia group and the control group (p = 0.008). After controlling for potential confounders, the multivariable adjusted odds ratio (OR) of macrosomia for those in the highest tertile of H19 mRNA level was 0.12 (95% CI: 0.02-0.59) when compared to those in the lowest tertile (p for linear trend = 0.009). Output:
0
3
NIv2
task848_pubmedqa_classification
zs_opt
[ { "content": "Instructions: Given a passage classify if the passage has a definite objective/aim/goal or not. Output '1' if the passage has a defininte objective/aim/goal and output '0' if the passage does not have a definite objective/aim/goal.\nInput: To investigate the associations between the mRNA levels of...
Teacher:You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Italian. Teacher: Now, understand the problem? Solve this instance: ولكن اعمل الأشياء التي تحبها Student:
Ma quel che conta è fare il lavoro con amore
6
NIv2
task1106_ted_translation_ar_it
zs_opt
[ { "content": "Teacher:You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Italian.\nTeacher: Now, understand the problem? Solve this instance: ولكن اعمل الأشياء التي تحبها\nStudent:", "role": "user" }, { "content": "Ma quel che conta è fare il lavoro con amore", ...
You will be given a definition of a task first, then some input of the task. You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Portugese. אבל אני יודע איפה היא היתה. Output:
Mas eu sei onde ela estava.
1
NIv2
task1114_ted_translation_he_pt
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nYou are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Portugese.\n\nאבל אני יודע איפה היא היתה.\nOutput:", "role": "user" }, { "content": "Mas eu sei onde ela estava.", "ro...
Detailed Instructions: 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. Problem:[8, 4, 3, 7, 8, 8, 5] , [3, 7, 1, 7, 7, 1, 8] Solution:
[3, 7, 8]
8
NIv2
task098_conala_list_intersection
zs_opt
[ { "content": "Detailed Instructions: 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 intersecti...
You will be given a definition of a task first, then some input of the task. Given a sentence in German, generate a new German sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true. Ein Mechanismus ist für die Bereitstellung einer Flucht Weg im Falle eines Brandes. Output:
Ein Fenster ist für die Bereitstellung einer Fluchtboje im Falle eines Brandes.
1
NIv2
task416_mickey_de_sentence_perturbation_generation
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nGiven a sentence in German, generate a new German sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated ...
Definition: You are given a target profession, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them. Input: Target: manager Managers train new employees. Kittens are cuddly creatures. Output:
unrelated
2
NIv2
task319_stereoset_classification_profession
zs_opt
[ { "content": "Definition: You are given a target profession, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of ...
In this task, you are given a premise sentence. Your task is to write a new sentence by substituting the subject and object (i.e., the input's subject should be output's object and vice versa.). The generated sentence must be fluent and shouldn't change the voice (i.e., passive or active) of the input. The tourist helped the scientists .
The scientists helped the tourist .
0
NIv2
task1364_hans_answer_generation
zs_opt
[ { "content": "In this task, you are given a premise sentence. Your task is to write a new sentence by substituting the subject and object (i.e., the input's subject should be output's object and vice versa.). The generated sentence must be fluent and shouldn't change the voice (i.e., passive or active) of the i...
Definition: You are given a sentence in English. Your job is to translate the English sentence into Persian. Input: The deep ocean is also gaining heat at a smaller rate, and energy is going into the net melting of ice all around the planet. Output:
اعماق اقیانوسها نیز در حال جذب گرما با میزان کمتری هستند وانرژی (گرما) باعث ذوب شدن شبکه یخ های اطراف سیاره [زمین] میشوند. اعماق اقیانوسها نیز در حال جذب گرما با میزان کمتری هستند وانرژی (گرما) باعث ذوب شدن شبکه یخ های اطراف سیاره [زمین] میشوند. اعماق اقیانوسها نیز در حال جذب گرما با میزان کمتری هستند وانرژی (گرما) باعث ذوب شدن شبکه یخ های اطراف سیاره [زمین] میشوند.
2
NIv2
task1093_ted_translation_en_fa
zs_opt
[ { "content": "Definition: You are given a sentence in English. Your job is to translate the English sentence into Persian.\nInput: The deep ocean is also gaining heat at a smaller rate, and energy is going into the net melting of ice all around the planet.\nOutput:", "role": "user" }, { "content": "...
In this task, you're given a review from Amazon. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good. Q: I’m so excited! These actually worked I was surprised! I’ve got three kids who love to spill their drinks at the restaurants!! Momma was prepared today! It is on the cups they give u at restaurants in picture. A:
5
4
NIv2
task1310_amazonreview_rating_classification
zs_opt
[ { "content": "In this task, you're given a review from Amazon. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good.\nQ: I’m so excited! These actually worked I was surprised! I’ve got three k...
Given the task definition and input, reply with output. In this task, you are given commands (in terms of logical operations) and natural interpretation of the given command to select relevant rows from the given table. Your job is to generate a label "yes" if the interpretation is appropriate for the command, otherwise generate label "no". Here are the definitions of logical operators: 1. count: returns the number of rows in the view. 2. only: returns whether there is exactly one row in the view. 3. hop: returns the value under the header column of the row. 4. and: returns the boolean operation result of two arguments. 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. 7. argmax/argmin: returns the row with the max/min value in header column. 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. 9. eq/not_eq: returns if the two arguments are equal. 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. 11. greater/less: returns if the first argument is greater/less than the second argument. 12. diff: returns the difference between two arguments. 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. 16. filter_all: returns the view itself for the case of describing the whole table 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument. Command: all_eq { all_rows ; played ; 30 }, interpretation: select the rows whose car make record fuzzily matches to pontiac . there is only one such row in the table . the driver record of this unqiue row is tony stewart .
no
5
NIv2
task211_logic2text_classification
zs_opt
[ { "content": "Given the task definition and input, reply with output. In this task, you are given commands (in terms of logical operations) and natural interpretation of the given command to select relevant rows from the given table. Your job is to generate a label \"yes\" if the interpretation is appropriate f...
Detailed Instructions: You will be given two pieces of text with the same meaning. One of them is simpler and easier to understand for non-native English speakers. Complex texts may contain more difficult words, have unnecessary phrases or contain long sentences. Your task is to choose the simpler piece of text. You are expected to output 'Text one' if the first sentence is simpler. Otherwise output 'Text two'. Problem:Text one: Solid metallic hydrogen consists of a crystal lattice of atomic nuclei. Most are protons. The spacing is significantly smaller than a Bohr radius. Text two: Solid metallic hydrogen consists of a crystal lattice of atomic nuclei. Most are protons. The spacing is significantly smaller than a Bohr radius. Solution:
Text one
8
NIv2
task112_asset_simple_sentence_identification
zs_opt
[ { "content": "Detailed Instructions: You will be given two pieces of text with the same meaning. One of them is simpler and easier to understand for non-native English speakers. Complex texts may contain more difficult words, have unnecessary phrases or contain long sentences. Your task is to choose the simpler...
Definition: Combine the given two facts to write a concluding fact. Note that there should be some parts of the first and second facts that are not mentioned in this conclusion fact. Your combined fact should be the result of a chain between the two facts. Chains form when two facts connect together to produce a concluding fact. An example of a chain is: "pesticides cause pollution" (fact1) + "pollution can harm animals" (fact2) → "pesticides can harm animals" (conclusion fact). Parts of the concluding fact overlap with the first and the second fact. To construct such a concluding fact, a useful way is to borrow the subject from one fact and the ending conclusions from another fact. Input: Fact 1: ultraviolet light causes sunburn. Fact 2: Furthermore, sunburn can cause premature aging and skin cancers. Output:
ultraviolet light can cause skin cancer.
2
NIv2
task038_qasc_combined_fact
zs_opt
[ { "content": "Definition: Combine the given two facts to write a concluding fact. Note that there should be some parts of the first and second facts that are not mentioned in this conclusion fact. Your combined fact should be the result of a chain between the two facts. Chains form when two facts connect togeth...
Instructions: In this task, you are given a sentence in either Spanish or English. Your task is to determine the language of the input sentence. Input sentences can only be in Spanish or English, and they cannot be in two languages ​​at the same time. Input: It seems to me that the Commission figures are aspirational. Output:
English
3
NIv2
task533_europarl_es-en_language_identification
zs_opt
[ { "content": "Instructions: In this task, you are given a sentence in either Spanish or English. Your task is to determine the language of the input sentence. Input sentences can only be in Spanish or English, and they cannot be in two languages ​​at the same time.\nInput: It seems to me that the Commission fig...
You will be given a definition of a task first, then some input of the task. You are given a question or fill-in-the-blank question, two answer options (Option1 and Option2) and an Explanation. Your task is to find the correct answer (return the string of the correct option, not option1/2) for the given question from the given options and using explanation. Question: If Mona is in space comparing the distance of certain planets from the Sun and she notices that Pluto is farther away then Neptune, which planet will have the larger orbit? Option1: Pluto Option2: Neptune Explanation: In general, the farther away from the Sun, the greater the distance from one planets orbit to the next. Output:
Pluto
1
NIv2
task178_quartz_question_answering
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nYou are given a question or fill-in-the-blank question, two answer options (Option1 and Option2) and an Explanation. Your task is to find the correct answer (return the string of the correct option, not option1/2) for th...
Detailed Instructions: In this task you will be given a list of numbers. You should remove any number that is not an integer (whole number). If every number is not an whole number then an empty list ("[]") should be returned. Otherwise, answer with the list of whole numbers separated by comma inside brackets. Q: [14.815, -7] A:
[-7]
9
NIv2
task367_synthetic_remove_floats
zs_opt
[ { "content": "Detailed Instructions: In this task you will be given a list of numbers. You should remove any number that is not an integer (whole number). If every number is not an whole number then an empty list (\"[]\") should be returned. Otherwise, answer with the list of whole numbers separated by comma in...
Detailed Instructions: You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example "trophy" and "suitcase". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question. | Attribute | triggerword | contrastive triggerword | | age | old | new | | altitude | low | high | | area | small | vast | | brightness | dark | light | | clarity | obscure | clear | | cleanness | dirty | clean | | complexity | simple | complex | | cost | cheap | expensive | | density | sparse | dense | | depth | shallow | deep | | distance | near | far | | electric conductivity | low | high | | flexibility | rigid | flexible | | granularity | fine | coarse | | hardness | soft | hard | | length | short | long | | magnitude | small | large | | mass | small | large | | odor | weak | strong | | pressure | low | high | | resistance | low | high | | shape | round | sharp | | shape | flat | spiky | | size | small | large | | sound | quiet | loud | | sound pitch | low | high | | speed | slow | fast | | stability | unstable | stable | | strength | weak | strong | | temperature | low | high | | texture | smooth | rough | | thermal conductivity | low | high | | thickness | thin | thick | | volume | small | large | | weight | light | heavy | | width | narrow | wide | | location | in | out | | location | up | down | | location | above | below | | location | on | off | | location | to | from | Q: Context Word: silk. A:
The fabric was a lot cheaper than the silk, because the _ was bottom of the line.
9
NIv2
task031_winogrande_question_generation_object
zs_opt
[ { "content": "Detailed Instructions: You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example \"trophy\" and \"suitcase\". The expected answer to your question must be one of the objects present in the s...
You will be given a definition of a task first, then some input of the task. In this task, you are given a tuple, comprising Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonX will be seen as what is mentioned in the Tail or not. In this task, PersonX will be seen as the Tail if the Tail describes PersonX's persona or attribute as perceived by others given an event. In the gift-giving example, X may be seen as generous or giving. In contrast, in an event such as PersonX steals a car, PersonX may be perceived as evil. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action. Head: PersonX graduates with a degree<sep>Tail: accomplished Output:
Yes
1
NIv2
task1199_atomic_classification_xattr
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a tuple, comprising Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by gene...
Definition: In this task, you are given a short passage that conveys a stereotype or an anti-stereotype. A stereotype is an over-generalized belief about a particular group of people(based on race, ethnicity, gender, age, abilities, etc.). An anti-stereotype is an idea that goes against a common stereotype. You are expected to classify the passage into two classes: stereotype or anti-stereotype. Input: Passage: If Andy had African genetics maybe he would be able to jump higher and not get hurt. Output:
Stereotype
2
NIv2
task316_crows-pairs_classification_stereotype
zs_opt
[ { "content": "Definition: In this task, you are given a short passage that conveys a stereotype or an anti-stereotype. A stereotype is an over-generalized belief about a particular group of people(based on race, ethnicity, gender, age, abilities, etc.). An anti-stereotype is an idea that goes against a common s...
In this task, you need to answer the given multiple-choice question on the gain. Gain is the value by which to multiply the input. Classify your answers into 'a', 'b', 'c', 'd', and 'e'. Q: Problem: a shopkeeper sold 30 articles at the cost price of 35 articles . then find the profit % or lost % Options: a ) 12 % , b ) 15 % , c ) 16.67 % , d ) 18 % , e ) 22 % A:
c
4
NIv2
task1419_mathqa_gain
zs_opt
[ { "content": "In this task, you need to answer the given multiple-choice question on the gain. Gain is the value by which to multiply the input. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\nQ: Problem: a shopkeeper sold 30 articles at the cost price of 35 articles . then find the profit % or lost % ...
In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining. Q: claim: Online Shopping Is Better Than Offline Shopping. perspective: Online shopping is fast. A:
support
4
NIv2
task738_perspectrum_classification
zs_opt
[ { "content": "In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.\nQ: claim: Online Shopping Is Better Than...
Instructions: In this task, you are given a question in English, and your task is to translate it into Persian. Input: What is the reason behind left hand drive and right hand drive in different countries? Output:
دلیل حرکت رانندگی چپ و راست در کشورهای مختلف چیست؟
3
NIv2
task652_parsinlu_en_fa_translation
zs_opt
[ { "content": "Instructions: In this task, you are given a question in English, and your task is to translate it into Persian.\nInput: What is the reason behind left hand drive and right hand drive in different countries?\nOutput:", "role": "user" }, { "content": "دلیل حرکت رانندگی چپ و راست در کشوره...
You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Farsi. Q: هناك وهم إدراكي: نحن ندرك أن الأخصائيون النفسيون يعرفون بأنه كلما كان أسهل أن نسترجع حالة خاصة لشيء ما, كلما زادت إحتمالية أن تكمل المشوار معها. A:
توهم شناختی هم وجود دارد. ما روانشناسان شناختی می ‌ دانیم که هرچقدر یادآوری موارد چیزی آسان ‌ تر باشد ، ما احتمال بیشتری به وقوع آن نسبت می ‌ دهیم.
4
NIv2
task1108_ted_translation_ar_fa
zs_opt
[ { "content": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Farsi.\nQ: هناك وهم إدراكي: نحن ندرك أن الأخصائيون النفسيون يعرفون بأنه كلما كان أسهل أن نسترجع حالة خاصة لشيء ما, كلما زادت إحتمالية أن تكمل المشوار معها.\nA: ", "role": "user" }, { "content": "توهم ...
Q: You are given a sentence from a conversation between a human and a virtual assistant. Your task is to identify which one of following five services the sentence is related to - Media, Travel, Flights, Buses, RideSharing Can you get me a cab? A:
RideSharing
7
NIv2
task881_schema_guided_dstc8_classification
zs_opt
[ { "content": "Q: You are given a sentence from a conversation between a human and a virtual assistant. Your task is to identify which one of following five services the sentence is related to - Media, Travel, Flights, Buses, RideSharing\nCan you get me a cab?\nA:", "role": "user" }, { "content": "Ri...
Q: In this task, you're given the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the beginning, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible. Middle: Kumail found a pair of jeans and put them on. Ending: Finally, he tossed on a purple sweatshirt to complete his outfit. A:
Kumail couldn't figure out what to wear.
7
NIv2
task072_abductivenli_answer_generation
zs_opt
[ { "content": "Q: In this task, you're given the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra i...
Q: In this task, you are given Twitter posts. Your task is to label the post's emotion (as expressed by the user) as sadness, joy, love, anger, fear, or surprise. ive seen the way serina feels strange if shes not being useful and it sure helps that the cleaner is pretty expensive and not having to pay that money would be pretty great A:
fear
7
NIv2
task512_twitter_emotion_classification
zs_opt
[ { "content": "Q: In this task, you are given Twitter posts. Your task is to label the post's emotion (as expressed by the user) as sadness, joy, love, anger, fear, or surprise.\nive seen the way serina feels strange if shes not being useful and it sure helps that the cleaner is pretty expensive and not having t...
Instructions: In this task, you are given a sentence in English, and your task is to translate it into Persian. Input: i don't know. Output:
نمي دونم؟
3
NIv2
task658_tep_en_fa_translation
zs_opt
[ { "content": "Instructions: In this task, you are given a sentence in English, and your task is to translate it into Persian.\nInput: i don't know.\nOutput:", "role": "user" }, { "content": "نمي دونم؟", "role": "assistant" } ]
Definition: In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input. Input: name[Loch Fyne], food[Japanese], customer rating[3 out of 5], area[riverside], near[The Rice Boat] Output:
There is a Japanese restaurant called Loch Fyne in riverside located near The Rice Boat. It has been rated 3 out of 5 by customers.
2
NIv2
task957_e2e_nlg_text_generation_generate
zs_opt
[ { "content": "Definition: In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input.\nInput: name...
In this task, you are given a paragraph, a question, and a candidate incorrect answer to the question. Your goal is to judge whether the provided answer is a valid incorrect answer to a given question. An incorrect answer should not truthfully answer the given question. A good incorrect answer should be closely related to the content of the paragraph and/or the question so that the readers are forced to read the whole paragraph to infer its [in]correctness. Additionally, an incorrect answer should be of the same semantic type as the given correct answer (e.g., both can be names of locations). If you think the given incorrect answer is good(and incorrect), indicate it by responding "Yes". Otherwise, respond "No". There are only two types of responses possible:"Yes" and "No". Paragraph- Sent 1: Two women trade houses without ever having met . Sent 2: They 're both looking for an escape from their problems , but by running away , both come to discover a great deal about themselves . Sent 3: Ria Lynch is married to Danny Lynch and they have a daughter and a son . Sent 4: Danny begins spending less and less time at home with his wife and children . Sent 5: Ria believes another baby is the solution , and is shocked to find out that indeed her husband is going to be a father - but to a child from an affair he has been having . Sent 6: Her husband 's unfaithfulness is the event that leads Ria into her decision to switch homes with a woman from the US called Marilyn who lost her teenage son to a motorcycle accident on his birthday . Sent 7: Marilyn is struggling to come to terms with her son 's death and has become estranged from her husband . Sent 8: She hopes her time in Dublin will cease her grief . Sent 9: Ria and Marilyn discover deep , dark secrets about the other during the summer . Sent 10: The two become close friends but do not reveal the secrets . Sent 11: { { Expand section } }. Question: What was the consequence of trading houses for both women? Incorrect Answer: They 're both looking for an escape from their problems , but by running away , both come to discover a great deal about themselves.
No.
0
NIv2
task057_multirc_classify_incorrect_answer
zs_opt
[ { "content": "In this task, you are given a paragraph, a question, and a candidate incorrect answer to the question. Your goal is to judge whether the provided answer is a valid incorrect answer to a given question. An incorrect answer should not truthfully answer the given question. A good incorrect answer sho...
Detailed Instructions: In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10. Problem:[-683, 413, -12, -452, -935, 363, -442, -850, 751, 825, -425, -822] Solution:
[-680, 410, -10, -450, -940, 360, -440, -850, 750, 820, -420, -820]
8
NIv2
task373_synthetic_round_tens_place
zs_opt
[ { "content": "Detailed Instructions: In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.\nProblem:[-683, 413, -12, -452, -935, 363, -442, -850, 751, 825, -425, -822]\nSolution:", "ro...
Detailed Instructions: In this task, you are given a sentence which is either in the Hindi language or English language. You task is to identify the language of input sentence. Input sentence can be in Hindi or English language only and also it cannot have two languages at a time. Q: Looked at from this angle , parliamentary questions are an essential aid to the Executive for they put into focus , areas of vital concern to the public at large . A:
English
9
NIv2
task427_hindienglish_corpora_hi-en_language_identification
zs_opt
[ { "content": "Detailed Instructions: In this task, you are given a sentence which is either in the Hindi language or English language. You task is to identify the language of input sentence. Input sentence can be in Hindi or English language only and also it cannot have two languages at a time.\nQ: Looked at fr...
Detailed Instructions: In this task, you need to count the number of vowels (letters 'a', 'e', 'i', 'o', 'u') / consonants (all letters other than vowels) in the given sentence. Problem:Sentence: 'a cow standing next to a fence with cows'. Count the number of vowels in the given sentence. Solution:
11
8
NIv2
task157_count_vowels_and_consonants
zs_opt
[ { "content": "Detailed Instructions: In this task, you need to count the number of vowels (letters 'a', 'e', 'i', 'o', 'u') / consonants (all letters other than vowels) in the given sentence.\nProblem:Sentence: 'a cow standing next to a fence with cows'. Count the number of vowels in the given sentence.\nSoluti...
Detailed Instructions: In this task, you are given a sentence in Arabic, and your task is to translate it into English. Q: هل يتضمن النساء ايضا ؟ A:
That doesn't include women?
9
NIv2
task650_opus100_ar_en_translation
zs_opt
[ { "content": "Detailed Instructions: In this task, you are given a sentence in Arabic, and your task is to translate it into English.\nQ: هل يتضمن النساء ايضا ؟\nA:", "role": "user" }, { "content": "That doesn't include women?", "role": "assistant" } ]
Definition: Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive. Input: I've been a longtime fan of Mercedes and own most of her Valdemar series. So, of course, I picked this book up at my local store. After wrestling through 50 pages, I gave up! I plan to sell it back to my local store ASAP- this is nothing better than a paperweight in my bookshelves. The worst part is, my boyfriend picked it up and tried reading it. Now he thinks that this is a good example of her work! Output:
Negative
2
NIv2
task493_review_polarity_classification
zs_opt
[ { "content": "Definition: Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.\nInput: I've been a longtime fan of Mercedes and own most of her Valdemar series. So, of course, I picked this book up at my local store. After wrestling through 50 pages, I ...
In this task, you need to replace a letter in the sentence with another given letter. Sentence: 'some people all holding forks and spoons over a small bowl of food'. Replace the letter 'i' with 'v' in the sentence.
some people all holdvng forks and spoons over a small bowl of food
0
NIv2
task160_replace_letter_in_a_sentence
zs_opt
[ { "content": "In this task, you need to replace a letter in the sentence with another given letter.\n\nSentence: 'some people all holding forks and spoons over a small bowl of food'. Replace the letter 'i' with 'v' in the sentence.", "role": "user" }, { "content": "some people all holdvng forks and ...
Definition: Given a pair of words, generate the relation between them. The first word is called the 'concept' and the second word is called the 'relatum' The relation must be one of the following: co-hyponym (coordinate), hypernym, meronym, attribute, event, or random. A coordinate relation indicates that the concept and relatum belong to the same semantic class. A hypernym relation indicates that the relatum is a category of which the concept is a specific instance. A meronym relation implies that relatum is a part/component/organ/member of the concept. An attribute relation is when the relatum is an adjective expressing an attribute of the concept. An event relation holds when the relatum is a verb referring to an action/activity/happening/event that is performed by or with the concept. If the relatum and concept are unrelated, the relation between them is 'random'. Classify your answers into coord, hyper, mero, attri, event, and random. Input: Concept: tanker, Relatum: travel. Output:
event
2
NIv2
task1418_bless_semantic_relation_classification
zs_opt
[ { "content": "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 indica...
This task is about identifying the subject of a given sentence. The subject of a sentence is the person, place, or thing that is performing the action of the sentence. The subject represents what or whom the sentence is about. Each sentence in this task is guaranteed to contain a single subject. The input is a sentence and the output is the identified subject of that sentence. The year when West Manila has a tariff increase of 6.5 was 2000.0.
2000
0
NIv2
task1411_dart_subject_identification
zs_opt
[ { "content": "This task is about identifying the subject of a given sentence. The subject of a sentence is the person, place, or thing that is performing the action of the sentence. The subject represents what or whom the sentence is about. Each sentence in this task is guaranteed to contain a single subject. T...
Instructions: In this task, you are given a sentence in the English and Hindi language. Your task is check if the Hindi sentence is translation of English. if the translation is correct than generate label "Yes", otherwise generate label "No". Input: English: The prosecution case has met with a number of procedural difficulties, with US District Court judge Emmet G. Sullivan holding the prosecution in contempt in March for failing to turn over documents concerning an FBI whistleblower's reports of mishandling of the case. Hindi: मुशर्रफ के अन्य विकल्पों में आपातकालीन स्थिति की घोषणा करना शामिल हो सकता है, जो उन्हें सेना का समर्थन पाने या संसद को भंग करने में सहायता कर सकता है, हालांकि इससे राजनीतिक अराजकता पैदा हो सकती है। Output:
No
3
NIv2
task434_alt_en_hi_answer_generation
zs_opt
[ { "content": "Instructions: In this task, you are given a sentence in the English and Hindi language. Your task is check if the Hindi sentence is translation of English. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".\nInput: English: The prosecution case has met with...
Detailed Instructions: In this task, you are given a news article. Your task is to classify the article to one out of the four topics 'World', 'Sports', 'Business', 'Sci/Tech' if the article's main topic is relevant to the world, sports, business, and science/technology, correspondingly. If you are not sure about the topic, choose the closest option. Note that URLs in the text have been replaced with [Link]. Q: #39;Halo 2 #39; hits stores Tuesday quot;Halo 2, quot; the follow-up to the 2001 best-selling video game, quot;Halo: Combat Evolved, quot; will be released Tuesday nationwide for the Microsoft Xbox video game console. A:
Sci/Tech
9
NIv2
task379_agnews_topic_classification
zs_opt
[ { "content": "Detailed Instructions: In this task, you are given a news article. Your task is to classify the article to one out of the four topics 'World', 'Sports', 'Business', 'Sci/Tech' if the article's main topic is relevant to the world, sports, business, and science/technology, correspondingly. If you ar...
Q: In this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase. Article: My first performance in front of an audience was coming up soon. I tried as hard as I could to keep calm, but my heart was racing. I stared down at my sweat-covered, shaking hands. I looked up again at the audience, realizing that these were real people. They were not just my mum and dad, who would say, "Good job!" even if I missed up the whole piece. What if I had the wrong music? What if I played the wrong notes? As it turned out, I was never able to answer these questions because the spotlight was waiting for me. I grasped my hands tightly together, drying off the sweat. Slowly I walked to the mud-brown piano in the centre of the room. It had 88 _ keys, which were waiting impatiently to be played. _ in my throat and sat down. Slowly, I opened the music. Next, I rested my still shaking hands on the keys. As my fingers played across the keys, I was becoming more unsure of my preparation for this moment. But the memory of my year of training came flooding back. I knew that I had practised this piece so many times that I could play it backwards if asked. Although at one point I accidently played two keys instead of the intended one, I continued to move my fingers automatically . My eyes burned holes into the page in front of me. There was no way that I was going to lose my concentration. To keep this promise to myself, I leaned forward and concentrated carefully on the music. When I came to the end of the page, a warning went off inside my head: don't make a mistake when you turn the page! Needless to say, I obeyed myself with all my heart and mind, and was proud of my "page-turning" feat . I finished the rest of the piece without making a single mistake. I had finished. I had mastered the impossible. Answer: her heart beat very fast. A:
Before the writer gave her first performance, _ .
7
NIv2
task649_race_blank_question_generation
zs_opt
[ { "content": "Q: In this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\nArticle: My first performance in front...
You will be given a definition of a task first, then some input of the task. You are given a sentence in English. Your job is to translate the English sentence into Portugese. Well, my team decided to do something really cool at the university. Output:
A minha equipa decidiu fazer uma coisa gira na universidade.
1
NIv2
task1094_ted_translation_en_pt
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nYou are given a sentence in English. Your job is to translate the English sentence into Portugese.\n\nWell, my team decided to do something really cool at the university.\nOutput:", "role": "user" }, { "conte...
Definition: You are given a sentence in Polish. Your job is to translate the Polish sentence into English. Input: Ale nadal nie czułem, że dzięki mnie świat staje się lepszy. Output:
But I still didn't feel like I was making the world a better place.
2
NIv2
task1256_ted_translation_pl_en
zs_opt
[ { "content": "Definition: You are given a sentence in Polish. Your job is to translate the Polish sentence into English.\nInput: Ale nadal nie czułem, że dzięki mnie świat staje się lepszy.\nOutput:", "role": "user" }, { "content": "But I still didn't feel like I was making the world a better place....
Detailed Instructions: You are given a sentence in Polish. Your job is to translate the Polish sentence into English. Problem:Organizujemy to co roku. Solution:
And we've continued to do it every year.
8
NIv2
task1256_ted_translation_pl_en
zs_opt
[ { "content": "Detailed Instructions: You are given a sentence in Polish. Your job is to translate the Polish sentence into English.\nProblem:Organizujemy to co roku.\nSolution:", "role": "user" }, { "content": "And we've continued to do it every year.", "role": "assistant" } ]
Definition: In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as "Inversion" or "Original" based on your judgment. Input: And, since he deals with the inner workings of it all, he's rather jaded on the whole thing. Output:
Original
2
NIv2
task428_senteval_inversion
zs_opt
[ { "content": "Definition: In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \...
Q: In this task, you will be presented with a passage, and you need to write an **implausible** answer to to fill in the place of "_". Your answer should be incorrect, but should not be out of context. Try using words that are related to the context of the passage, but are not the correct answer. Even though there exist multiple wrong answers, we only need a single wrong answer. Jamie Vardy wrote his name into the Premier League record books, with the Leicester striker's opener in the 1-1 draw against Manchester United the 11th consecutive game in which he has found the target. Vardy latched onto Christian Fuchs' pinpoint ball down the channel to beat David de Gea with a rifled shot across goal to give Claudio Ranieri's side the lead after 24 minutes at the King Power Stadium. It was the 28-year-old's 13th goal in 11 Premier League appearances - his 14th in total for the season - and the former Fleetwood Town striker will now set his sights on eclipsing Jimmy Dunne's record of scoring in 12 consecutive games in the 1930s with Sheffield United.Jamie Vardy put Leicester ahead against Manchester United to set a new Premier League record on SaturdayStriker drilled past David de Gea to score historic goal and eclipse Ruud van Nistelrooy's tally in 10 straight games28-year-old began his incredible run of scoring in the 1-1 draw with Bournemouth back on August 29Van Nistelrooy was quick to congratulate the striker on Instagram for having overtaken him in the scoring chartsVardy will look to set a new all-time record of goals in consecutive league games set by Jimmy Dunne in the 1930s Question:Vardy kick-started his run with a penalty against newly-promoted opposition in the shape of _. A:
Jamie Vardy
7
NIv2
task303_record_incorrect_answer_generation
zs_opt
[ { "content": "Q: In this task, you will be presented with a passage, and you need to write an **implausible** answer to to fill in the place of \"_\". Your answer should be incorrect, but should not be out of context. Try using words that are related to the context of the passage, but are not the correct answer...
Detailed Instructions: In this task, you are given a sentence in Persian, and your task is to translate it into English. Q: اسمت چيه جان استورم . A:
whats your name john storm .
9
NIv2
task659_tep_fa_en_translation
zs_opt
[ { "content": "Detailed Instructions: In this task, you are given a sentence in Persian, and your task is to translate it into English.\nQ: اسمت چيه جان استورم .\nA:", "role": "user" }, { "content": "whats your name john storm .", "role": "assistant" } ]
You will be given a definition of a task first, then some input of the task. In this task, you're given a context, a question, three options, and an answer. Your task is to classify whether the given answer is correct or not by providing 'Yes' or 'No', based on the context with commonsense reasoning about social situations. Context: Cameron provided care to individuals with special needs in a care home. Question: What will Others want to do next? Options: (A) give good care (B) selfish (C) Train to become a nurse like Cameron Answer: C Output:
No
1
NIv2
task579_socialiqa_classification
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a context, a question, three options, and an answer. Your task is to classify whether the given answer is correct or not by providing 'Yes' or 'No', based on the context with commonsense reason...
Q: In this task, You are given an open-domain question that can be answered based on factual information. Your task is to provide \*short\* answer (in a few words only) for the given question. The short answer can be one or more entities or it can also be boolean \*yes\* or \*no\*. who sings one way or another in coyote ugly A:
actress Piper Perabo
7
NIv2
task582_naturalquestion_answer_generation
zs_opt
[ { "content": "Q: In this task, You are given an open-domain question that can be answered based on factual information. Your task is to provide \\*short\\* answer (in a few words only) for the given question. The short answer can be one or more entities or it can also be boolean \\*yes\\* or \\*no\\*.\nwho sing...
Q: Given a paragraph, generate a claim that is supported by the given paragraph. 1) The claim must contain information from within the paragraph. 2) A sentence within the paragraph can be used as a claim. 3) The claim should not have contradictions within the paragraph. 4) The claim should be at most one sentence long. "SInce the test drug is in the very early stages of development, this criterion is technically not applicable. However, the present treatment regimen of an interferon and ribavirin costs thousands of dollars monthly for 6-12 months and it is likely that any newer antivirals will be additive and not replacements. A comment on the potential for significant additional costs would have been desirable. The story got a little carried away here. It said participants treated with the experimental drug had a ""dramatic"" reduction in viral load. While this may be true, it would have been helpful to point out, as the HealthDay story did, that the study lasted only a few days. We don’t know whether this benefit can be maintained over a longer period of time, especially considering that the hepatitis C virus has proven to be quite capable of developing resistance to antivirals over time. The story says study participants who took the drug exhibited ""few side effects."" But what were those side effects and how serious were they? The story doesn’t say. While the implication here is that the drug seems to be safe — a conclusion that we can’t really draw based on a small, early phase test — the story does include a cautionary quote from an expert about the need for additional testing to demonstrate safety. It also noted that patients taking this drug might still need to be treated with interferon, which many individuals can’t tolerate because of side effects. A close one, but we’ll call it satisfactory. This story includes appropriate caveats about the early nature of this research and includes a restraining quote from an expert who warns that the drug might not make it out of phase II tests. Unlike the competing HealthDay piece, this story resisted getting too worked up about the other experimental drugs for hepatitis-C that are closer to potential FDA approval. This story does not exaggerate the prevalence or severity of hepatitis C. According to disclosure statements from a 2008 CME program, Dr. Bruce Bacon, an expert source for this story, received research funding from Bristol Myers Squibb, which is developing the experimental drug being discussed. He also is a consultant to drug companies developing competing drugs for hepatitis C. To avoid the appearance of a conflict of interest it is desirable to identify relationships such as these clearly. This story fails to do so. The story compares the new drug with intravenously administered peg-interferon and ribavirin — the current standard of care for hepatitis C. The story called the research on BMS-790052 ""preliminary"" and made it clear that the drug was not close to approval. It also was more cautious than the competing HealthDay piece in its description of two other antiviral drugs that are nearing FDA approval. The story notes that there are many other drugs being developed to treat hepatitis C. It explained that a potentially novel advantage of the new compound is that it seems to be effective against all genotypes. We can’t be sure whether this story relied on a news release." A:
Experimental Drug May Treat Hepatitis C
7
NIv2
task1368_healthfact_sentence_generation
zs_opt
[ { "content": "Q: Given a paragraph, generate a claim that is supported by the given paragraph. 1) The claim must contain information from within the paragraph. 2) A sentence within the paragraph can be used as a claim. 3) The claim should not have contradictions within the paragraph. 4) The claim should be at m...
Q: In this task, you are given a hateful post in Bengali that expresses hate or encourages violence towards a person or a group based on the protected characteristics such as race, religion, sex, and sexual orientation. You are expected to classify the post into two classes: political or non-political depending on the topic. তুই তারাতারি দেশে আয় ভাই তারেক জিয়া A:
political
7
NIv2
task1491_bengali_political_hate_speech_binary_classification
zs_opt
[ { "content": "Q: In this task, you are given a hateful post in Bengali that expresses hate or encourages violence towards a person or a group based on the protected characteristics such as race, religion, sex, and sexual orientation. You are expected to classify the post into two classes: political or non-polit...
Q: A text is given in Bengali. Translate it from the Bengali language to the Panjabi language. The translation must not omit or add information to the original sentence. আজ আমাদের জন্য গর্বের বিষয় হল যে, মূল্যবৃদ্ধিকে নিয়ন্ত্রণ করে আমাদের উন্নয়নের হার বাড়ানোর উপযোগী একটি সমীকরণ নিয়ে এগিয়ে চলেছি। A:
ਮਹਿੰਗਾਈ ਅਤੇ ਵਿਕਾਸ ਵਿੱਚ ਸੰਤੁਲਨ - ਅੱਜ ਸਾਡੇ ਲਈ ਮਾਣ ਦਾ ਵਿਸ਼ਾ ਹੈ ਕਿ ਮਹਿੰਗਾਈ ਨੂੰ control ਕਰਦੇ ਹੋਏ ਅਸੀਂ ਵਿਕਾਸ ਦਰ ਨੂੰ ਵਧਾਉਣ ਵਾਲੇ ਇੱਕ ਅਹਿਮ ਸਮੀਕਰਣ ਨੂੰ ਲੈ ਕੇ ਚੱਲੇ ਹਾਂ।
7
NIv2
task1025_pib_translation_bengali_punjabi
zs_opt
[ { "content": "Q: A text is given in Bengali. Translate it from the Bengali language to the Panjabi language. The translation must not omit or add information to the original sentence.\nআজ আমাদের জন্য গর্বের বিষয় হল যে, মূল্যবৃদ্ধিকে নিয়ন্ত্রণ করে আমাদের উন্নয়নের হার বাড়ানোর উপযোগী একটি সমীকরণ নিয়ে এগিয়ে চ...
Instructions: In this task, you are given a sentence in the English language and your task is to convert it into the Hindi language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun). Input: However, New Zealand isn't the most up-to-date country with implementing similar legislation, Farrar says, “We are in fact almost the last country in the OECD to have such legislation.” Output:
हालांकि, न्यूज़ीलैंड समान कानून लागू करने वाला सर्वाधिक अद्यतित देश नहीं है, फ़र्रार कहते हैं, "हम वास्तव में OECD में ऐसा कानून रखने वाले लगभग आखिरी देश हैं।"
3
NIv2
task432_alt_en_hi_translation
zs_opt
[ { "content": "Instructions: In this task, you are given a sentence in the English language and your task is to convert it into the Hindi language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).\nInput: However, New Zealand isn't the mo...
In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head happens before the Tail or not. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action. Head: PersonX adapts to PersonY's environment<sep>Tail: to relax
No
0
NIv2
task1206_atomic_classification_isbefore
zs_opt
[ { "content": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the eve...
Definition: In this task, you're given a story (which contains five sentences only). Your task is to find all the characters which are available in the given story. Input: Sentence1: Tim was tired of how his apartment looked. Sentence2: He wanted to try something different. Sentence3: Tim spent all weekend redecorating. Sentence4: At the end he didn't like the new way. Sentence5: Tim returned it to how it used to be. Output:
Tim
2
NIv2
task292_storycommonsense_character_text_generation
zs_opt
[ { "content": "Definition: In this task, you're given a story (which contains five sentences only). Your task is to find all the characters which are available in the given story.\nInput: Sentence1: Tim was tired of how his apartment looked. Sentence2: He wanted to try something different. Sentence3: Tim spent a...
Given the task definition and input, reply with output. Languages typically provide more than one grammatical construction to express certain types of messages. Your task is to generate a senetence with the same meaning as given sentence, but with different grammatical construction. John distributed a team from work some books
John distributed some books to a team from work
5
NIv2
task132_dais_text_modification
zs_opt
[ { "content": "Given the task definition and input, reply with output. Languages typically provide more than one grammatical construction to express certain types of messages. Your task is to generate a senetence with the same meaning as given sentence, but with different grammatical construction.\n\nJohn distri...
Teacher:In this task, you will be presented with a text and a pronoun. You should write the name that the pronoun refers to. Position of the pronoun in the text is showed within two "_"s. Teacher: Now, understand the problem? Solve this instance: She then went on to study accounting at the University of Alaska and simultaneously worked at Wien Alaska Airlines to pay her way through school. On 29 October 1954, she married Hugh Fate, Jr., who would become a dentist and Native Americans rights activist. The couple had three daughters, Janine, Jennifer and Julie. After _her_ marriage, Fate returned to work at Wien Alaska Airlines. <sep>, Pronoun: her Student:
Fate
6
NIv2
task330_gap_answer_generation
zs_opt
[ { "content": "Teacher:In this task, you will be presented with a text and a pronoun. You should write the name that the pronoun refers to. Position of the pronoun in the text is showed within two \"_\"s.\nTeacher: Now, understand the problem? Solve this instance: She then went on to study accounting at the Univ...
Teacher:In this task, you will be presented with a question having multiple possible answers in Italian language. And you should choose a most suitable option out of "A", "B", "C", "D", and "E" based on your commonsense knowledge. Teacher: Now, understand the problem? Solve this instance: Question: L'avvocato ha spiegato che cos'è stato lo spergiuro, questo è stato un grande caso con un alto cosa? Options: A arrestare B vergogna C tensione D rischio E pena Student:
C
6
NIv2
task1143_xcsr_it_commonsense_mc_classification
zs_opt
[ { "content": "Teacher:In this task, you will be presented with a question having multiple possible answers in Italian language. And you should choose a most suitable option out of \"A\", \"B\", \"C\", \"D\", and \"E\" based on your commonsense knowledge.\nTeacher: Now, understand the problem? Solve this instanc...
Definition: In this task, You are given an open-domain question that can be answered based on factual information. Your task is to provide \*short\* answer (in a few words only) for the given question. The short answer can be one or more entities or it can also be boolean \*yes\* or \*no\*. Input: who sings learn to love again with pink Output:
Nate Ruess
2
NIv2
task582_naturalquestion_answer_generation
zs_opt
[ { "content": "Definition: In this task, You are given an open-domain question that can be answered based on factual information. Your task is to provide \\*short\\* answer (in a few words only) for the given question. The short answer can be one or more entities or it can also be boolean \\*yes\\* or \\*no\\*.\...
In this task, the input is a set of dialogues between a user and an assistant. You need to find the dialogue that is basically a response given to a question or an aspect of the user. Q: Sorry, I don't have that information, but one interestinfg fact is that the nearest part of the Continental Europe is mainland Norway, about 970km away, while mainland North America is 2070 km away. In 2009, Iceland became the first country with an openly gay head of government when Johanna Sigueoardotir became prime minister. What more is there to know about their politics Sorry, I don't have that information, but one interesting fact is that Iceland is a juncture of the North Atlantic and Artic Ocean. Is Iceland the coldest region of the world A:
In 2009, Iceland became the first country with an openly gay head of government when Johanna Sigueoardotir became prime minister.
4
NIv2
task576_curiosity_dialogs_answer_generation
zs_opt
[ { "content": "In this task, the input is a set of dialogues between a user and an assistant. You need to find the dialogue that is basically a response given to a question or an aspect of the user.\nQ: Sorry, I don't have that information, but one interestinfg fact is that the nearest part of the Continental Eu...
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. Q: sentence: Sam took French classes from Adam , because he was eager to speak it fluently . aspect: Adverb A:
Sam recently took French classes from Adam , because he was eager to speak it fluently .
4
NIv2
task275_enhanced_wsc_paraphrase_generation
zs_opt
[ { "content": "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:\n 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, ch...
Q: You are given a sentence in Italian. Your job is to translate the Italian sentence into Spanish. Ma ha avuto anche un fantastico effetto collaterale, che ho capito completamente solo poco tempo fa. Ho capito che acconsentire a giocare con le mie figlie, probabilmente ha salvato la mia carriera. A:
Pero también tuvo un efecto secundario sorprendente que comprendí completamente solo hace poco, cuando entendí que decir sí y jugar con mis hijas probablemente salvó mi carrera.
7
NIv2
task1249_ted_translation_it_es
zs_opt
[ { "content": "Q: You are given a sentence in Italian. Your job is to translate the Italian sentence into Spanish.\nMa ha avuto anche un fantastico effetto collaterale, che ho capito completamente solo poco tempo fa. Ho capito che acconsentire a giocare con le mie figlie, probabilmente ha salvato la mia carriera...
Given the task definition and input, reply with output. In this task, you need to reverse all words of a given length in the sentence. The number of letters in a word determine its length. For example, the length of the word "apple" is 5. Sentence: 'a crowd of people standing below a gray cloudy sky'. Reverse all words of length '6' in the given sentence.
a crowd of elpoep standing below a gray yduolc sky
5
NIv2
task378_reverse_words_of_given_length
zs_opt
[ { "content": "Given the task definition and input, reply with output. In this task, you need to reverse all words of a given length in the sentence. The number of letters in a word determine its length. For example, the length of the word \"apple\" is 5.\n\nSentence: 'a crowd of people standing below a gray clo...
In this task, you're given reviews from Amazon's food products and a summary of that review. Your task is to classify whether the given summary matches the original review. Generate "True" if the given review and its summary match, otherwise generate "False". Reviews: What was this, a waste off my time and money. Summary: Don’t waste your money, it’s worse than the last one.
True
0
NIv2
task1309_amazonreview_summary_classification
zs_opt
[ { "content": "In this task, you're given reviews from Amazon's food products and a summary of that review. Your task is to classify whether the given summary matches the original review. Generate \"True\" if the given review and its summary match, otherwise generate \"False\".\n\nReviews: What was this, a waste...
Detailed Instructions: The provided file includes inquiries about restaurants, and we ask you to translate those to the Arabic 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. Q: give me reviews for " jade buffet " . A:
اعرض لي تقييمات " jade buffet " .
9
NIv2
task250_spl_translation_en_ar
zs_opt
[ { "content": "Detailed Instructions: The provided file includes inquiries about restaurants, and we ask you to translate those to the Arabic 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 yo...
You will be given a definition of a task first, then some input of the task. Given a sentence with a missing word, pick the answer option that best fills out the missing word in the sentence. Indicate each answer with its index ('a', 'b', 'c', 'd'). Slugs have ____ noses.\Question: Choose the right answer from options given a) one b) four c) ten d) two Output:
b
1
NIv2
task1360_numer_sense_multiple_choice_qa_generation
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nGiven a sentence with a missing word, pick the answer option that best fills out the missing word in the sentence. Indicate each answer with its index ('a', 'b', 'c', 'd').\n\nSlugs have ____ noses.\\Question: Choose the...
Teacher:In this task, you are given product reviews about dvds. The goal is to classify the review as "POS" if the overall sentiment of the review is positive(the reviewer is satisfied) or as "NEG" if the overall sentiment of the review is negative(the reviewer is not satisfied). Teacher: Now, understand the problem? Solve this instance: Ryan Gives Standout Portrayal in Noir Misfire . Robert Ryan never delivered a bad performance. His memorable portrayal of a Tokyo crime boss is the best thing in "House of Bamboo" (1955) -- director Samuel Fuller's flat attempt at Japanese film noir. Ryan easily towers over Robert Stack's routine characterization, which looks like a dry run for "The Untouchables." Apart from Ryan and Joseph MacDonald's on-location CinemaScope photography, this reworking of the superior "Street With No Name" (1948) collapses at the starting gate. A major disappointment Student:
NEG
6
NIv2
task477_cls_english_dvd_classification
zs_opt
[ { "content": "Teacher:In this task, you are given product reviews about dvds. The goal is to classify the review as \"POS\" if the overall sentiment of the review is positive(the reviewer is satisfied) or as \"NEG\" if the overall sentiment of the review is negative(the reviewer is not satisfied).\nTeacher: Now...
In this task, you are given a text which is the body of a document. You are given a question and options. Pick the correct number. Don't generate anything else apart from the numbers provided in options. Q: Context: So Much So Fast is a documentary written and directed by Academy Award nominees Steven Ascher and Jeanne Jordan. This film premiered in competition at the 2006 Sundance Film Festival and won the Audience Award at the Boston Independent Film Festival. Question: The document can be classified to which topic? Options: 1)Animal, 2)Artist, 3)Film, 4)Album A:
3
4
NIv2
task633_dbpedia_14_answer_generation
zs_opt
[ { "content": "In this task, you are given a text which is the body of a document. You are given a question and options. Pick the correct number. Don't generate anything else apart from the numbers provided in options.\nQ: Context: So Much So Fast is a documentary written and directed by Academy Award nominees S...
You are given an elementary science question along with a few answer options. List all the words from the question that are essential and sufficient for choosing the correct answer option. Keep in mind that essential words are necessary to understand the meaning of the given question. However, non-essential words provide little information needed to select the correct answer. You can think about it like this: If the question was in another language, knowing the meaning of which words were necessary and enough for you to understand the question and answer it?. If your answer consists of multiple spans of words from the question, separate those using a comma (", "). Do not generate any word that is not present in the question. Make sure that your response is contained in the given question and the words are in the same order as the question. Grammatical correctness is not important. Q: Question: Which landforms are most like hills but are much taller? (A) caves (B) mountains (C) plains (D) valleys? A:
landforms, hills, taller?
4
NIv2
task044_essential_terms_identifying_essential_words
zs_opt
[ { "content": "You are given an elementary science question along with a few answer options. List all the words from the question that are essential and sufficient for choosing the correct answer option. Keep in mind that essential words are necessary to understand the meaning of the given question. However, non...
Detailed Instructions: In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time. Q: Statement: ( Doonesbury 's Duke character is not the only Thompson cartoon. Choices: 1. Thompson only makes one cartoon. 2. Thompson is an accomplished cartoonist. 3. Thompson has cartoons besides Doonesbury's Duke character. A:
2
9
NIv2
task201_mnli_neutral_classification
zs_opt
[ { "content": "Detailed Instructions: In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement...
Definition: In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. Here are the definitions of logical operators: 1. count: returns the number of rows in the view 2. only: returns whether there is exactly one row in the view 3. hop: returns the value under the header column of the row 4. and: returns the boolean operation result of two arguments 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column 6. nth max/nth min: returns the n-th max/n-th min of the values under the header column 7. argmax/argmin: returns the row with the max/min value in header column 8. nth argmax/nth argmin: returns the row with the n-th max/min value in header column 9. eq/not eq: returns if the two arguments are equal 10. round eq: returns if the two arguments are roughly equal under certain tolerance 11. greater/less: returns if argument 1 is greater/less than argument 2 12. diff: returns the difference between two arguments 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 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 argument 3 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3 Input: eq { hop { argmax { all_rows ; total } ; nation } ; australia } = true Output:
select the row whose total record of all rows is maximum . the nation record of this row is australia .
2
NIv2
task110_logic2text_sentence_generation
zs_opt
[ { "content": "Definition: In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. \n Here are the definitions of logical operators: \n 1. count: returns the number of rows ...
Definition: You are given a sentence in Persian. Your job is to translate the Farsi sentence into Arabic. Input: اینها انتخاب نیستند. Output:
لا تمثل هذه أي خيارات.
2
NIv2
task1268_ted_translation_fa_ar
zs_opt
[ { "content": "Definition: You are given a sentence in Persian. Your job is to translate the Farsi sentence into Arabic.\nInput: اینها انتخاب نیستند.\nOutput:", "role": "user" }, { "content": "لا تمثل هذه أي خيارات.", "role": "assistant" } ]
You will be given a definition of a task first, then some input of the task. In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether it is plausible for the Head to desire the Tail or not. In this task, desire means desires of sentient entities. For example, doctors likely desire to cure a patient. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action. Head: PersonX applies sunscreen<sep>Tail: to squeeze sunscreen into their hands Output:
No
1
NIv2
task1213_atomic_classification_desires
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic wor...
You will be given a definition of a task first, then some input of the task. You will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For consistency, answers should be in all lower cased letters. Category: BY THE SEASHORE Clue: The dried skeleton of this invertebrate resembles a large white coin Output:
sand dollar
1
NIv2
task305_jeopardy_answer_generation_normal
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nYou will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For consistency, answers should be in all lower cased let...
Q: In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that seamlessly connects with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes more sense. Title: Bathroom. Sentence 1: The bathroom was starting to smell strange. Sentence 2: The tub was backed up with an odd colored liquid. Sentence 3: I used a plunger on the drain. Sentence 4: A giant ball of hair extracted itself. Choices: a. I went home feeling a lot better knowing I was healthy. b. I threw it away, feeling sickened. A:
b
7
NIv2
task213_rocstories_correct_ending_classification
zs_opt
[ { "content": "Q: In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that seamlessly connects with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are pl...
You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from "sympathetic" to "stern"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them. Context Word: Enamel. Question: PersonX applied enamel to remove the paint from the walls of PersonY's house because _ needed work. Answer: PersonX
PersonX applied enamel to remove the paint from the walls of PersonY's house because _ hired him.
0
NIv2
task035_winogrande_question_modification_person
zs_opt
[ { "content": "You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). ...
Detailed Instructions: You need to create a question containing a blank (_), based on the given context word. Your question must contain two persons --PersonX and PersonY. The expected answer to your question must be PersonX. PersonX and PersonY should not be equally likely to fill the blank. There should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your question. Avoid repeating the same style, pattern, or phrases in each question, try to increase diversity by varying sentence structure, blank placement, etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Person X and Person Y have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Problem:Context Word: manage. Solution:
It was easy for PersonX but not PersonY to manage the office because _ was good with people.
8
NIv2
task032_winogrande_question_generation_person
zs_opt
[ { "content": "Detailed Instructions: You need to create a question containing a blank (_), based on the given context word. Your question must contain two persons --PersonX and PersonY. The expected answer to your question must be PersonX. PersonX and PersonY should not be equally likely to fill the blank. Ther...
Detailed Instructions: In this task, you are given a sentence in the Swedish language and a corresponding English translation of the Swedish sentence. Your task is to generate a label "Yes" if the translation is correct, otherwise generate label "No". Q: Swedish: Jag önskar er en fortsatt bra dag. English: I wish you a good evening. A:
Yes
9
NIv2
task314_europarl_sv-en_classification
zs_opt
[ { "content": "Detailed Instructions: In this task, you are given a sentence in the Swedish language and a corresponding English translation of the Swedish sentence. Your task is to generate a label \"Yes\" if the translation is correct, otherwise generate label \"No\".\nQ: Swedish: Jag önskar er en fortsatt bra...
Detailed Instructions: A text is given in English. Translate it from the English language to the Hindi language. The translation must not omit or add information to the original sentence. Problem:उन्होंने जेएनयू में लगे नारों का भी उल्लेख करते हुए कहा कि कुछ विपक्षी पार्टियां उनका समर्थन करती हैं जो लोग देश तोड़ने की बात करते हैं। Solution:
They must clarify whether they want terrorism to continue and bloodshed to go on in the country.
8
NIv2
task1024_pib_translation_hindi_english
zs_opt
[ { "content": "Detailed Instructions: A text is given in English. Translate it from the English language to the Hindi language. The translation must not omit or add information to the original sentence.\nProblem:उन्होंने जेएनयू में लगे नारों का भी उल्लेख करते हुए कहा कि कुछ विपक्षी पार्टियां उनका समर्थन करती हैं...
In this task, you will be presented with a question having multiple possible answers in Swahili language. And you should choose a most suitable option out of "A", "B", "C", "D", and "E" based on your commonsense knowledge. Question: Mtaalam alimwambia lazima awasilishe shida zake, akasema kuwa tayari tu kufanya nini? Options: A andika kwa nambari B sikiliza C ongea na watu D zungumza na watu E kutuma barua pepe
C
0
NIv2
task1144_xcsr_sw_commonsense_mc_classification
zs_opt
[ { "content": "In this task, you will be presented with a question having multiple possible answers in Swahili language. And you should choose a most suitable option out of \"A\", \"B\", \"C\", \"D\", and \"E\" based on your commonsense knowledge.\n\nQuestion: Mtaalam alimwambia lazima awasilishe shida zake, aka...
In this task, you will be presented with a passage and have to answer a question based on your understanding of the events inferred from the passage. Among the entities, try to find the best entity that is most likely to fill in "_" and classify the answers based on options. Q: Near Mosul, Iraq (CNN) Iraqi forces entered ISIS-held Mosul on Thursday for the first time in more than two years, and are in a head-to-head battle with militants on the front line, defense officials said. Iraqi Defense Ministry spokesman Brig. Gen. Tahsin Ibrahim told CNN that units of the 9th Armored Division had entered the key city and that troops had stormed the neighborhood of al Intisar in the east. Penetrating the eastern border has been the most significant breakthrough in the offensive, which was launched two weeks ago to free Mosul from the militant group's brutal rule. Officials had warned that entering the city would likely trigger the fiercest fighting yet, and that the battle is expected to be fought "street to street," or even "house to house."Iraqi security forces kill two ISIS suicide bombers in eastern MosulEntering the city is a significant breakthrough, but troops face enormous challenges Questions:Now they say _ teenagers wearing suicide vests are riding around the eastern neighborhoods of the city on motorbikes. (A) Mosul (B) Iraq (C) CNN (D) Iraqi (E) ISIS (F) Iraqi Defense Ministry (G) Tahsin Ibrahim (H) 9th Armored Division (I) al Intisar A:
(E)
4
NIv2
task302_record_classification
zs_opt
[ { "content": "In this task, you will be presented with a passage and have to answer a question based on your understanding of the events inferred from the passage. Among the entities, try to find the best entity that is most likely to fill in \"_\" and classify the answers based on options.\nQ: Near Mosul, Iraq...
You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation. Q: Sentence1: What type of food would you like? Sentence2: You're welcome, please call us again in the future. Have a great day. Sentence3: Great that is all I need. Thanks. Sentence4: Perfect. I need a table for 1 at 19:45 on thursday. Sentence5: I am glad the Cambridge TownInfo centre helped you. Goodbye. Sentence6: I am in the mood for Chinese food, please. Sentence7: OK I have that booked the reference number is EBZIPGV2 . Sentence8: I want to find an expensive restaurant located in Cambridge centre. Sentence9: Will do! Thank you, hope you have an amazing day as well. Sentence10: I have found 4 restaurants that fit that description. How does HK Fusion sound? Question: Who has spoken the sentence 1? (A) User (B) System A:
Answer: (B) System
4
NIv2
task638_multi_woz_classification
zs_opt
[ { "content": "You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.\nQ: Sentence1: What type of food would you like? Sentence2: You're welcome, please call us again in the future. Have a great day. Sentence3: Great that is all I need. T...
Definition: In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words. Input: In the industrial field, the positron annihilation is not affected by complex environment, and the gamma-ray photon penetration is strong, so the nondestructive detection of industrial parts can be realized. Due to the poor image quality caused by gamma-ray photon scattering, attenuation and short sampling time in positron process, we propose the idea of combining deep learning to generate positron images with good quality and clear details by adversarial nets. The structure of the paper is as follows: firstly, we encode to get the hidden vectors of medical CT images based on transfer Learning, and use PCA to extract positron image features. Secondly, we construct a positron image memory based on attention mechanism as a whole input to the adversarial nets which uses medical hidden variables as a query. Finally, we train the whole model jointly and update the input parameters until convergence. Experiments have proved the possibility of generating rare positron images for industrial non-destructive testing using countermeasure networks, and good imaging results have been achieved. Output:
adversarial nets, attention mechanism, positron images, data scarcity
2
NIv2
task668_extreme_abstract_summarization
zs_opt
[ { "content": "Definition: In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words.\nInput: In the industrial field, the positron annihilation is not affected by comple...
You will be given a definition of a task first, then some input of the task. In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head is located or can be found at/in/on the Tail or not. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action. Head: board<sep>Tail: building Output:
Yes
1
NIv2
task1207_atomic_classification_atlocation
zs_opt
[ { "content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic wor...
Detailed Instructions: In this task, you're given a question, along with three passages, 1, 2, and 3. Your job is to determine which passage can be used to answer the question by searching for further information using terms from the passage. Indicate your choice as 1, 2, or 3. Q: Question: Did Columbia University have more students enrolled than MIT did the year Wasson was born? Passage 1:1999: Britney Spears was the big winner of the night winning four awards, including Best New Act and Best Song for "...Baby One More Time". She also performed during the ceremony, entertaining the crowd with a medley of her songs "...Baby One More Time" and "(You Drive Me) Crazy". The Free Your Mind Award, which honours an individual or organisation for aiding in humanitarian efforts and fighting prejudice, was given to Bono for his world peace work. Puff Daddy performed "My Best Friend" backed by a full gospel choir, followed by Iggy Pop, who stagedived into the crowd during the track "Lust for Life". Whitney Houston sang a medley of "Get It Back" and "My Love Is Your Love", while Mariah Carey performed "Heartbreaker". Marilyn Manson, who wore nothing but a G-string, closed the show with a performance of "Rock Is Dead". Passage 2:Wasson was born Isabel Deming Bassett in Brooklyn, NY on January 11, 1897, daughter of urban planner Edward Bassett and Annie Preston Bassett, and sister of inventor and engineer Preston Bassett. Wasson graduated Phi Beta Kappa from Wellesley College in 1918, majoring in history so she could take a wide range of science courses. She took classes in geology after graduation at the University of Chicago and the Massachusetts Institute of Technology. She met her future husband, petroleum geologist Theron Wasson, whom she married in 1920, while working towards a master's degree in geology at Columbia University, which she finished in 1934. They had three children: Elizabeth W. Bergstrom, a biologist; Edward B. Wasson, a petroleum geologist; and Anne Harney Gallagher, an art historian. Wasson worked as a petroleum geologist in her husband's office at the Pure Oil Company from the early 1920s until 1928. She published two scholarly articles on geology, one co-authored with her husband about an oil field discovered by Pure Oil in 1914, and another by herself about the ages of rock formations in Ohio and new terminology for them; the latter was cited in a number of other papers and a recent book. After 1928 she spent over 50 years in River Forest, IL, teaching science in the local public schools, lecturing, bird watching (ornithology), and mentoring generations of young naturalists. She was quoted in this 1986 Chicago Tribune article as an expert on local geology at age 89. She was honored for her contributions to local history in 1982 when the Wasson Room was named after her in a local school to hold local history resources. Her interests included archaeology; she discovered a Native American religious mound in Thatcher Woods, near her house in River Forest, in the 1930s. An article about her discovery called her "the one who started the environmental education movement in America back in the 1920s and '30s." Theron and Isabel divorced in 1953 and she did not remarry. From 1953-1954, Wasson served as President of the Chicago Ornithological Society. Wasson also taught classes at the Morton Arboretum in Lisle, Illinois. She died in La Grange Park, IL, in 1994. Passage 3:Born in Bedford on 22 September 1780, John Hensman was educated at Bedford School and at Corpus Christi College, Cambridge, where he matriculated as an Exhibitioner in February 1797. He graduated as ninth Wrangler at the University of Cambridge in 1801 and was elected as a Fellow of Corpus Christi College, Cambridge. He was ordained in 1803, and was appointed as Curate of Wraxall, Somerset. In 1809 he was appointed as Curate of Clifton, Bristol. He was instrumental in the rebuilding of Clifton parish church, which was consecrated on 12 August 1822. He was then the moving force behind the building of the Church of Holy Trinity, Hotwells, which was consecrated on 10 November 1830. He held the incumbency of the church until 1844, when he was granted the perpetual curacy of Christ Church, Clifton Down, and he oversaw the rebuilding of that church. He was instituted to the living of Clifton, Bristol, in 1847, and oversaw the building of St Paul's Church, Clifton, Bristol, consecrated in 1853, and St Peter’s Church, Clifton, consecrated in 1855. A:
2
9
NIv2
task230_iirc_passage_classification
zs_opt
[ { "content": "Detailed Instructions: In this task, you're given a question, along with three passages, 1, 2, and 3. Your job is to determine which passage can be used to answer the question by searching for further information using terms from the passage. Indicate your choice as 1, 2, or 3.\nQ: Question: Did C...
Given a sentence in English language, translate the sentence to Somali language keeping the meaning of the original sentence intact English sentence: 29 Then I said unto them, What is the high place whereunto ye go? And the name thereof is called Bamah unto this day.
29 Markaasaan ku idhi, Meesha sare oo aad tagtaan maxay tahay? Ilaa maantadan la joogo waxaa magaceeda la yidhaahdaa Baamaah.
0
NIv2
task446_opus_paracrawl_en_so_translation
zs_opt
[ { "content": "Given a sentence in English language, translate the sentence to Somali language keeping the meaning of the original sentence intact\n\nEnglish sentence: 29 Then I said unto them, What is the high place whereunto ye go? And the name thereof is called Bamah unto this day.", "role": "user" }, ...
Given the task definition and input, reply with output. You are given a sentence in Persian. Your job is to translate the Farsi sentence into Polish. (تشویق حضار) اما این یکی به صورت مضحکی ایده رو مطرح می ‌ کند ، دیروز هم درباره ساعت ده هزار سالی دنی هیلیس صحبت کردیم. یک موتور اینجا در سمت چپ داریم ، که از قطاری از چرخ دنده می ‌ گذرد.
(Oklaski) To z kolei jest zabawna, konceptualna praca, wczoraj mówiliśmy o 10 000 - letnim zegarze Danny 'ego Hillisa mamy tu silnik po lewej stronie, który przechodzi przez ciąg zębatek,
5
NIv2
task1272_ted_translation_fa_pl
zs_opt
[ { "content": "Given the task definition and input, reply with output. You are given a sentence in Persian. Your job is to translate the Farsi sentence into Polish.\n\n(تشویق حضار) اما این یکی به صورت مضحکی ایده رو مطرح می ‌ کند ، دیروز هم درباره ساعت ده هزار سالی دنی هیلیس صحبت کردیم. یک موتور اینجا در سمت چپ د...