source
stringlengths
17
501k
target
stringlengths
0
8.23k
task_name
stringlengths
8
85
task_source
stringclasses
4 values
template_type
stringclasses
4 values
template_idx
int64
0
17
split
stringclasses
3 values
Use reasoning to lead to the answer of the following question: What can sex often be? Options: - nice - good - dirty - great fun - eventful Reasoning process:
Sex is usually fun. Sex leads to enjoyment hence it is often great fun. Therefore, the final answer is great fun.
cot_ecqa
CoT
zs_opt
5
train
Use reasoning to lead to the answer of the following question: Subway stations are generally found in a? Options: - large city - london - big city - toronto - chicago Reasoning process:
Subway stations are generally found in a big city. Therefore, the final answer is big city.
cot_ecqa
CoT
zs_opt
5
train
What could happen to guns if they are wet? Options: - misfire - explode - jam - break - take life Let's solve it slow. Misfire means fail to discharge or fire properly. The gunpowder in gun gets wet when guns are wet. Wet gunpowder fails to fire properly.... So the answer is misfire. Minerals can be found on what third rock from the sun? Options: - nebraska - multivitamin - michigan - ore - earth Let's solve it slow. Earth is third from sun. Earth is type of giant rock in universe.... So the answer is earth. A boss may like an employee's ambition, so the employee may get put what? Options: - in charge of project - conquer opponent - go to school - begin work - webisode Let's solve it slow. Ambition means a strong desire to achieve something. People with a strong desire to achieve something are generally put in charge of projects.... So the answer is in charge of project. If a person is supported by those closest to them what do they have? Options: - support group - get enough sleep - nice family - strong bones - compliments
Let's solve it slow. People closest to a person is called his family. When one is supported by closest people, he has a nice family.... So the answer is nice family.
cot_ecqa
CoT
fs_opt
7
train
QUESTION: What do parents tell their kids to stop doing when they want them to go to sleep? Options: - get in bed - get dance - get into bed - stop talking - lay down ME: The answer is stop talking CoT: Kids generally keep chit chatting in bed without trying to sleep. Chit chatting means talking continuously. When someone keeps chit chatting they are asked to stop talking.. QUESTION: Manny refused to give the court respect, and was charged with what? Options: - dishonor - contempt - humiliate - disdain - scorn ME: The answer is contempt CoT: One can be charged with contempt. When you disregard a court, you are held responsible for it which is held contempt.. QUESTION: When people eat more food than they need on a daily basis, what tends to happen? Options: - become angry - obesity - gain weight - agree or disagree - pay bills ME: The answer is gain weight CoT: Each person has a basic specific calorie requirement based on their lifestyle. When people eat more than their requirement, the extra calories get stored in the form of fat in the body. Due to increased fat in the body, people usually gain weight.. QUESTION: What does a town make up a small part of? Options: - rural areas - city - countryside - train station - state ME:
The answer is state CoT: A town makes up a small part of state..
cot_ecqa
CoT
fs_opt
0
train
q: Why does a bodybuilder eat so much? Options: - pleasant conversation - store food for winter - satisfy hunger - sounds of digestion - gain weight a: Body builder needs to gain muscle in bulking phase. Gainig muscle requires to eat more calories and result in gaining weight. The answer is gain weight QUESTION: He didn't want his son to be soft, so he was always what on him? Options: - hard - sandpaper - loud - firm - abrasive ANSWER: Hard is the opposite of soft. As he didn't want his son to be soft so he was always hard on him. The answer is hard q: A hard piece of rubber deflected off a stick and flew up and struck a fan, this could only happen at a what? Options: - sporting event - hockey game - living room - soccer game - football stadium a: Hockey stick have rubber for grip that may get deflected sometime and can get stuck a fan. Stick is used in hockey game to play. The answer is hockey game QUESTION: Where should you keep your mustard after it's been opened? Options: - jar - hot dog - hamburger - fast food restaurant - refrigerator ANSWER: Mustard is kept in refrigerator. A refrigerator is used to keep things safe from getting rotten. Mustard when kept in open can get rotten. The answer is refrigerator q: What does getting in line for a long time require in a person? Options: - intention - getting in the front of the line - basic organization - early childhood socialization - patience a: Patience is the capacity to accept or tolerate delay, problems, or suffering without becoming annoyed or anxious. Getting in line for a long time requires tolerating delay and not becoming annoyed. The answer is patience q: Marmot's can be found in high places. They have hands that they can use to get to the top of what? Options: - outside - hill - jungle - rocky hillside - tree a:
Marmots are found on trees. Trees are high places. The answer is tree
cot_ecqa
CoT
fs_opt
1
train
QUESTION: To learn must have the right book, to work efficiently what must one have? Options: - improve yourself - become knowledgeable - have tools - persistence - have more knowledge ANSWER: Have tools means to have any instrument or simple piece of equipment that you hold in your hands and use to do a particular kind of work. To learn must have the right book, to work efficiently one must have tools. The answer is have tools QUESTION: A newspaper is a traditional way of doing what to events? Options: - announce - defend - educate - communicate - inform ANSWER: Events can be communicated. Newspaper can communicate events to everyone. There are traditional ways of communication. The answer is communicate QUESTION: What's black and white and contains many a story? Options: - past - book or magazine - novel - newspaper - story book ANSWER: Newspaper is black and white. Its a newspaper that contains many a story. The answer is newspaper QUESTION: What is something you do in a bank? Options: - make noise - have tea - make time - make payments - take time ANSWER:
You can make payments in a bank. Making payments is an activity that is done by a person in a bank. The answer is make payments
cot_ecqa
CoT
fs_opt
4
train
Where is a nightclub likely to be? Options: - manhattan - downtown area - beside a river - building - major city Let's think carefully first. Step-by-step reasoning process:
Nightclubs are in posh areas like downtown areas. So the final answer is downtown area.
cot_ecqa
CoT
zs_opt
9
train
QUESTION: Billy is an archaeologist. He looks for information about ancient human civilization. What is something that he might enjoy finding? Options: - school - love - adventure - space shuttle - library ANSWER: Library means a collection of books for use or borrowing by member. Billy can enjoy finding books of ancient human civilization in a library. The answer is library q: John left his plates secure in his belief that someone else would get it and went out with a full belly. Where was john eating? Options: - dining room - shelf - restaurant - cupboard - stomach a: People do not have to clean their own plate at a restaurant. People can eat their food and leave without worrying about the plate. The answer is restaurant QUESTION: Where is one unlikely to get popcorn? Options: - restaurant - movie house - soccer game - carnival - movie theater ANSWER: Soccer game does not have popocorn as it has balls and players. The answer is soccer game q: Where could a person avoid the rain? Options: - bus stop - tunnel - synagogue - fairy tale - street corner a: People tend to go indoors with a roof when it is raining outside. A synagogue is a safe indoor place with a roof. A person can go to a synagogue to avoid the rain. The answer is synagogue QUESTION: What is a psychological benefit of having fun? Options: - glee - stress relief - smiling - twinkle - may laugh ANSWER: Having fun causes happiness and relief from all stress and tensions. Stress and tensions are psychological issues. The answer is stress relief QUESTION: Joe was gentle when he was setting the cup on the table, because it didn't want to make any what? Options: - distractions - water mark - put down - noise - picks up ANSWER:
Cup makes noise when set on table. If you gentally set cup on tanle, it may not make noise. The answer is noise
cot_ecqa
CoT
fs_opt
0
train
Where could you find a laundry room that is only used by staff? Options: - house - hotel - green house - college - dorm Step-by-step reasoning process below:
Hotel is an establishment providing accommodation, meals and other services for travellers and tourists. You find a laundry room that is only used by staff at Hotel. The answer: hotel.
cot_ecqa
CoT
zs_opt
1
test
q: What are you buying at the general store when you buy a box full of black and red chips? Options: - old west - nachos - salt - shopping mall - checkers a: Checkers is a board game played between two people on an 8x8 checked board. The answer is checkers q: Where can one attend a famous bazaar? Options: - china - festival - istanbul - arabia - india a: There are a lot of famous bazaars in India. One can attend a famous bazaar where there are a lot of famous bazaars. The answer is india q: What would you be unable to do if you are bathing and your hands are wet? Options: - dry skin - slip and fall - read a book - using soap - reading newspaper a:
Newspaper gets wet and torn if it gets in contact with water. People’s hands are wet with water when they are bathing. The answer is reading newspaper
cot_ecqa
CoT
fs_opt
6
validation
Teacher: A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. Teacher: Now, understand the problem? If you are still confused, see the following example: ഇന്ന് ഒരു വിദൂരസ്ഥ ഗ്രാമത്തിലെ പാവപ്പെട്ട പൗരന് തന്റെ അവകാശങ്ങള്‍ നേടുന്നതിനായി ദീര്‍ഘദൂരം യാത്ര ചെയ്യേണ്ടതായോ ഇടനിലക്കാര്‍ക്ക് കൈക്കൂലി കൊടുക്കേണ്ടതായിട്ടോ ഇല്ല Solution: دور دراز گاؤں میں غریب شہریوں کو سفر کرنے کے لئے کافی طویل سفر کرنے کے لئے کافی نہیں ہے Reason: Correct translation for given sentence. Input sentence means 'There is no longer enough to travel long enough to travel the poor citizen in a remote village' which is the same as the output sentence. Now, solve this instance: 6 വരെ ലക്ഷം കോടിയാണെന്നും, അനുമതി നല്‍കിയ പദ്ധതികള്‍ പൂര്‍ത്തീകരിക്കാന്‍ തന്നെ വര്‍ഷങ്ങള്‍ വേണ്ടി വരുമെന്നും മന്ത്രി പറഞ്ഞു. Student:
6 لاکھ کروڑ روپے سالانہ ہو ں تو سبھی منظور شدہ پروجیکٹوں کی تکمیل میں کئی دہائیاں لگ جائیں گی۔
task1059_pib_translation_malayalam_urdu
NIv2
fs_opt
2
train
A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. Let me give you an example: ഇന്ന് ഒരു വിദൂരസ്ഥ ഗ്രാമത്തിലെ പാവപ്പെട്ട പൗരന് തന്റെ അവകാശങ്ങള്‍ നേടുന്നതിനായി ദീര്‍ഘദൂരം യാത്ര ചെയ്യേണ്ടതായോ ഇടനിലക്കാര്‍ക്ക് കൈക്കൂലി കൊടുക്കേണ്ടതായിട്ടോ ഇല്ല The answer to this example can be: دور دراز گاؤں میں غریب شہریوں کو سفر کرنے کے لئے کافی طویل سفر کرنے کے لئے کافی نہیں ہے Here is why: Correct translation for given sentence. Input sentence means 'There is no longer enough to travel long enough to travel the poor citizen in a remote village' which is the same as the output sentence. OK. solve this: 2018-19 ലെ ബജറ്റ് എസ്റ്റിമേറ്റിനെക്കാള്‍ 21% വിഹിതം വര്‍ദ്ധിപ്പിച്ച് 2019-20 ല്‍ 58,166 കോടി രൂപയാക്കി. Answer:
19-2018 کے بجٹ کے مقابلے میں 20-2019 کے بجٹ میں 21 فی صد کا اضافہ کرکے 58166 کروڑ روپے مختص کئے گئے۔
task1059_pib_translation_malayalam_urdu
NIv2
fs_opt
8
train
A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. Example: ഇന്ന് ഒരു വിദൂരസ്ഥ ഗ്രാമത്തിലെ പാവപ്പെട്ട പൗരന് തന്റെ അവകാശങ്ങള്‍ നേടുന്നതിനായി ദീര്‍ഘദൂരം യാത്ര ചെയ്യേണ്ടതായോ ഇടനിലക്കാര്‍ക്ക് കൈക്കൂലി കൊടുക്കേണ്ടതായിട്ടോ ഇല്ല Example solution: دور دراز گاؤں میں غریب شہریوں کو سفر کرنے کے لئے کافی طویل سفر کرنے کے لئے کافی نہیں ہے Example explanation: Correct translation for given sentence. Input sentence means 'There is no longer enough to travel long enough to travel the poor citizen in a remote village' which is the same as the output sentence. Problem: കല്‍രാജ് മിശ്രയെ ഹിമാചല്‍ പ്രദേശ് ഗവര്‍ണറായി നിയമിച്ച്‌കൊണ്ടുള്ള വിജ്ഞാപനവുംരാഷ്ട്രപതി ഭവന്‍ പുറപ്പെടുവിച്ചു.
Solution: جناب کل راج مشرا کو ہماچل پردیش کا گورنر مقرر کیاگیا ہے۔
task1059_pib_translation_malayalam_urdu
NIv2
fs_opt
5
train
Teacher: A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. Teacher: Now, understand the problem? If you are still confused, see the following example: ഇന്ന് ഒരു വിദൂരസ്ഥ ഗ്രാമത്തിലെ പാവപ്പെട്ട പൗരന് തന്റെ അവകാശങ്ങള്‍ നേടുന്നതിനായി ദീര്‍ഘദൂരം യാത്ര ചെയ്യേണ്ടതായോ ഇടനിലക്കാര്‍ക്ക് കൈക്കൂലി കൊടുക്കേണ്ടതായിട്ടോ ഇല്ല Solution: دور دراز گاؤں میں غریب شہریوں کو سفر کرنے کے لئے کافی طویل سفر کرنے کے لئے کافی نہیں ہے Reason: Correct translation for given sentence. Input sentence means 'There is no longer enough to travel long enough to travel the poor citizen in a remote village' which is the same as the output sentence. Now, solve this instance: 2018 ഓഗസ്റ്റില്‍ കേരളത്തില്‍ കനത്ത മഴയുണ്ടാകുമെന്ന് കാലാവസ്ഥാ മുന്നറിയിപ്പുകള്‍ നല്‍കിയിരുന്നു Student:
کیرالامیں اگست 2018میں زبردست بارش کے بارے میں جاری کی گئی موسم سے متعلق وارننگ
task1059_pib_translation_malayalam_urdu
NIv2
fs_opt
2
train
Teacher:A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. Teacher: Now, understand the problem? Solve this instance: ഭഗത് സിംഗ്, രാജ്ഗുരു, സുഖ്‌ദേവ് എന്നിവരുടെ രക്തസാക്ഷി ദിനത്തില്‍ പ്രധാനമന്ത്രിയുടെ ശ്രദ്ധാജ്ഞലി Student:
بھگت سنگھ، راج گورو اور سکھ دیو کو ان کے یوم شہادت پر وزیراعظم کا خراج عقیدت
task1059_pib_translation_malayalam_urdu
NIv2
zs_opt
6
train
A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. Q: യോന്‍സി സര്‍വകലാശാലയില്‍ ഗാന്ധിജിയുടെ അര്‍ദ്ധകായ പ്രതിമ അനാച്ഛാദനം ചെയ്യാന്‍ സാധിച്ചത് ഒരു ബഹുമതിയാണെന്ന് തദവസരത്തില്‍ പ്രധാനമന്ത്രി പറഞ്ഞു. A:
اس موقع پر اپنی تقریر میں وزیراعظم نے یونسائی یونیورسٹی میں بابو کے نیم قد مجسمہ کی نقاب کشائی کو اپنے لئے ایک اعزاز قرار دیا۔
task1059_pib_translation_malayalam_urdu
NIv2
zs_opt
4
train
A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. അവരുടെ പ്രവര്‍ത്തനക്ഷമതയില്‍ തനിക്കു പൂര്‍ണ വിശ്വാസമുണ്ടെന്നും അദ്ദേഹം വ്യക്തമാക്കി.
م ن۔م ع ۔ ن ا۔ (06-04-17)
task1059_pib_translation_malayalam_urdu
NIv2
zs_opt
0
train
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task. A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. ഇന്ന് ഒരു വിദൂരസ്ഥ ഗ്രാമത്തിലെ പാവപ്പെട്ട പൗരന് തന്റെ അവകാശങ്ങള്‍ നേടുന്നതിനായി ദീര്‍ഘദൂരം യാത്ര ചെയ്യേണ്ടതായോ ഇടനിലക്കാര്‍ക്ക് കൈക്കൂലി കൊടുക്കേണ്ടതായിട്ടോ ഇല്ല Solution: دور دراز گاؤں میں غریب شہریوں کو سفر کرنے کے لئے کافی طویل سفر کرنے کے لئے کافی نہیں ہے Why? Correct translation for given sentence. Input sentence means 'There is no longer enough to travel long enough to travel the poor citizen in a remote village' which is the same as the output sentence. New input: നിത്യാനന്ദ റായ് Solution:
جناب نتیانند رائے
task1059_pib_translation_malayalam_urdu
NIv2
fs_opt
0
train
A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. [Q]: തപാല്‍ അദാലത്ത് ഈ മാസം 21 ന് [A]: الیکٹرانکس اور اطلاعات تکنالوجی کی وزارت [Q]: സിക്കിമിലെ നാംച്ചി, ഗാംഗ്‌ടോക്ക്, അരുണാചല്‍ പ്രദേശിലെ ഇറ്റാനഗര്‍, പാസിഘട്ട്, ത്രിപുരയിലെ അഗര്‍ത്തല എന്നിവിടങ്ങളിലെ കമാന്റ് ആന്റ് കണ്‍ട്രോള്‍ സെന്ററുകളുടെ ശിലാഫലകം പ്രധാനമന്ത്രി ഡിജിറ്റല്‍ മാര്‍ഗ്ഗത്തിലൂടെ അനാവരണം ചെയ്തു. [A]: وزیراعظم نے ریاست سکم میں نامچی اور گانگٹاک ، اروناچل پردیش میں ایٹا نگر اور پاسی گھاٹ نیز تریپورہ کے اگرتلہ میں کمان اینڈ کنٹرول مراکز کی تختی کی ڈیجیٹلی رونمائی کی۔ [Q]: സാമ്പത്തിക ഉള്‍ച്ചേരല്‍ സൂക്ഷ്മ, ചെറുകിട, ഇടത്തരം സംരംഭങ്ങളിലേക്കും വ്യാപിച്ചിട്ടുണ്ട്. [A]:
مالیاتی شمولیت بہت چھوٹے ، چھوٹے اور درمیانہ درجے کے کاروبار کی توسیع میں بھی مدد حاصل ہوتی ہے ۔
task1059_pib_translation_malayalam_urdu
NIv2
fs_opt
5
test
A text is given in Malayalam. Translate it from the Malayalam language to the Urdu language. The translation must not omit or add information to the original sentence. [EX Q]: പരിഷ്‌ക്കാരങ്ങള്‍ റെയില്‍വേയുടെ പ്രവര്‍ത്തനം മെച്ചപ്പെടുത്തുന്നതിന് ഗണ്യമായ സാമ്പത്തിക, ഭരണ അധികാരങ്ങള്‍ ജനറല്‍ മാനേജര്‍മാര്‍ക്കും ഡിവിഷണല്‍ റെയില്‍വേ മാനേജര്‍മാര്‍ക്കും ഫീല്‍ഡ് ഉദ്യോഗസ്ഥര്‍ക്കും നല്‍കി. മെച്ചപ്പെട്ട മേല്‍നോട്ടത്തിന് എല്ലാ റെയില്‍വേ ഡിവിഷണല്‍ ഓഫീസുകളിലും അഡീഷണല്‍ ഡിവിഷണല്‍ റെയില്‍വേ മാനേജര്‍മാരുടെ പോസ്റ്റുകള്‍ അനുവദിച്ചു. [EX A]: لوگوں کو ڈیجیٹل لین دین پر راغب کرنے کے لئے ای ٹکٹ بک کرنے پر سروس چارج ختم کردیا ہے۔ ای ٹکٹ پر دس لاکھ کے مفت بیمہ کی پیش کش کی ہے اور ڈیجیٹل طریقے سے خریدے جانے والے سیزن ٹکٹوں پر 0. [EX Q]: ദേശീയ സുരക്ഷാ ഉപദേഷ്ടാവ് ശ്രീ. അജിത്ത് ഡോവലും കൂടിക്കാഴ്ചയില്‍ സന്നിഹിതനായിരുന്നു. [EX A]: اس موقع پر قومی سلامتی کے مشیر جناب اجیت ڈوال بھی موجود تھے۔ [EX Q]: ഭഗത് സിംഗ്, രാജ്ഗുരു, സുഖ്‌ദേവ് എന്നിവരുടെ രക്തസാക്ഷി ദിനത്തില്‍ പ്രധാനമന്ത്രിയുടെ ശ്രദ്ധാജ്ഞലി [EX A]:
بھگت سنگھ، راج گورو اور سکھ دیو کو ان کے یوم شہادت پر وزیراعظم کا خراج عقیدت
task1059_pib_translation_malayalam_urdu
NIv2
fs_opt
6
validation
Teacher: In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. Teacher: Now, understand the problem? If you are still confused, see the following example: What college did this president attend? Where did this president meet his wife? Solution: Did this president meet his wife in college? Reason: This is a good question. By combining "meet wife" and "college" we get to a new question. Now, solve this instance: What tree is most populous in this national park? Does this national park have caves you can enter without a permit? Student:
Which cave is the longest at this national park?
task121_zest_text_modification
NIv2
fs_opt
2
train
Q: In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. Did this president have both a son and a daughter? Was this president born on the east coast? A:
When were the children of this president born?
task121_zest_text_modification
NIv2
zs_opt
7
train
Part 1. Definition In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. Part 2. Example What college did this president attend? Where did this president meet his wife? Answer: Did this president meet his wife in college? Explanation: This is a good question. By combining "meet wife" and "college" we get to a new question. Part 3. Exercise Does this dog breed usually weigh 25 pounds or more fully grown? Is this dog breed commonly used as a watch dog for farm animals? Answer:
Do this dog breed get large enough to be used as a watch dog for farm animals?
task121_zest_text_modification
NIv2
fs_opt
7
train
In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. [Q]: Does this dog breed have short legs compared to the size of its body? Is this dog breed a human created mix of other breeds? [A]: Has this dog breed been created from other breeds so that it has short legs? [Q]: What are the medical names for common diseases of this dog breed? What is the top of the average life expectancy of this dog breed? [A]: Do the common diseases for this dog breed affect average life expectancy? [Q]: Can this dog breed have black or brown spots? Is this dog breed usually covered with at least two colors of fur? [A]:
Does this dog breed have spots of two different colors?
task121_zest_text_modification
NIv2
fs_opt
5
train
In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. Q: What is the natural tail length of this dog breed? Is this dog breed usually covered with at least two colors of fur? A:
What colors is the tail of this dog breed?
task121_zest_text_modification
NIv2
zs_opt
4
train
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task. In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. What college did this president attend? Where did this president meet his wife? Solution: Did this president meet his wife in college? Why? This is a good question. By combining "meet wife" and "college" we get to a new question. New input: What did this president major in during their college studies? How did the stock market perform while this president was in office? Solution:
Did this president major in economics or business?
task121_zest_text_modification
NIv2
fs_opt
0
train
In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. Q: Can this dog breed have black or brown spots? Is white an acceptable color for this dog breed? A: Can this dog breed be white, black, or brown? **** Q: What was the maiden name of the mother of this president? Was the wife of this president born in the united states? A: What is the maiden name of the wife of this president? **** Q: Is white an acceptable color for this dog breed? Can a dog from this dog breed have only one color on their fur? A:
Is white the only acceptable color for this dog breed? ****
task121_zest_text_modification
NIv2
fs_opt
4
train
In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. [EX Q]: What types of boating activities are available in this national park? Does this national park provide facilities for grilling? [EX A]: Can you boat and grill at this national park? [EX Q]: Does this dog breed have long and straight fur? Does this dog breed prefer colder climates? [EX A]: Will long and straight fur of this dog breed keep it warm in colder climates? [EX Q]: Did this president decrease the budget deficit by the end of his term? Who did this president win the presidential election against? [EX A]:
Who did this president inherit the budget deficit from?
task121_zest_text_modification
NIv2
fs_opt
6
train
Detailed Instructions: In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. See one example below: Problem: What college did this president attend? Where did this president meet his wife? Solution: Did this president meet his wife in college? Explanation: This is a good question. By combining "meet wife" and "college" we get to a new question. Problem: Is the fur of this dog breed longer than an inch? How long should the tails of this dog breed be when docked? Solution:
Are the docked tails of this dog breed longer than an inch?
task121_zest_text_modification
NIv2
fs_opt
4
test
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task. In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. What college did this president attend? Where did this president meet his wife? Solution: Did this president meet his wife in college? Why? This is a good question. By combining "meet wife" and "college" we get to a new question. New input: Does this national park feature more than two restaurants? Where can i eat in this national park? Solution:
Are there more than two places to eat in this national park?
task121_zest_text_modification
NIv2
fs_opt
0
validation
Generate a correct and concise answer for the question based on the words in the context. One example is below. Q: Context : Isaac Nicola Romero (1916 in Havana, Cuba -- 1997) was a prominent Cuban guitarist and one of the founders of the modern Cuban Guitar School. Question : What was Isaac Nicola's city of birth? A: Havana Rationale: According to context Issac Nicola's city of birth is Havana. Hence this is a correct output. Q: Context : Lena Baker (June 8, 1900 -- March 5, 1945) was an African American maid who was falsely accused of capital murder by the state of Georgia in 1945 for killing her white employer, Ernest Knight, and executed by the state. Question : Which crime Lena Baker is considered to have commited? A:
murder
task1327_qa_zre_answer_generation_from_question
NIv2
fs_opt
9
train
Detailed Instructions: Generate a correct and concise answer for the question based on the words in the context. Problem:Context : Blind Guys (Hungarian: Vakvagányok) is a 2001 Hungarian drama film directed by Péter Tímár. Question : Who served as director for Blind Guys? Solution:
Péter Tímár
task1327_qa_zre_answer_generation_from_question
NIv2
zs_opt
8
train
Instructions: Generate a correct and concise answer for the question based on the words in the context. Input: Context : Brandy Fisher (born October 28, 1975) played ice hockey for the New Hampshire Wildcats women's ice hockey program and was the first ever winner of the Patty Kazmaier Award, awarded to the top female ice hockey player in the NCAA. Question : Which describes the sex or gender of Brandy Fisher? Output:
female
task1327_qa_zre_answer_generation_from_question
NIv2
zs_opt
3
train
Instructions: Generate a correct and concise answer for the question based on the words in the context. Input: Context : Rhythm Is It! is a 2004 German documentary film directed by Thomas Grube and Enrique Sánchez Lansch. Question : Under whose direction was Rhythm Is It! produced? Output:
Enrique Sánchez Lansch
task1327_qa_zre_answer_generation_from_question
NIv2
zs_opt
3
train
Teacher:Generate a correct and concise answer for the question based on the words in the context. Teacher: Now, understand the problem? Solve this instance: Context : East End Hustle is a 1976 drama film directed by Frank Vitale and distributed by Troma Entertainment. Question : The production company responsible for East End Hustle is what? Student:
Troma Entertainment
task1327_qa_zre_answer_generation_from_question
NIv2
zs_opt
6
train
Q: Generate a correct and concise answer for the question based on the words in the context. Context : USS Bermuda (1861) was a large steamer captured by the Union Navy during the American Civil War. Question : What conflict involved USS Bermuda (1861)? A:
American Civil War
task1327_qa_zre_answer_generation_from_question
NIv2
zs_opt
7
train
Given the task definition, example input & output, solve the new input case. Generate a correct and concise answer for the question based on the words in the context. Example: Context : Isaac Nicola Romero (1916 in Havana, Cuba -- 1997) was a prominent Cuban guitarist and one of the founders of the modern Cuban Guitar School. Question : What was Isaac Nicola's city of birth? Output: Havana According to context Issac Nicola's city of birth is Havana. Hence this is a correct output. New input case for you: Context : Birkenia is a genus of extinct anaspid fish from Middle Silurian strata of Northern Europe, and Middle Silurian to possibly Earliest Devonian strata of Arctic Canada. Question : Is the taxon rank of Birkenia species or genus? Output:
genus
task1327_qa_zre_answer_generation_from_question
NIv2
fs_opt
1
train
Detailed Instructions: Generate a correct and concise answer for the question based on the words in the context. See one example below: Problem: Context : Isaac Nicola Romero (1916 in Havana, Cuba -- 1997) was a prominent Cuban guitarist and one of the founders of the modern Cuban Guitar School. Question : What was Isaac Nicola's city of birth? Solution: Havana Explanation: According to context Issac Nicola's city of birth is Havana. Hence this is a correct output. Problem: Context : X-FEN is an extension of Forsyth-Edwards Notation (FEN). Question : Which is the basis of X-FEN? Solution:
Forsyth-Edwards Notation
task1327_qa_zre_answer_generation_from_question
NIv2
fs_opt
4
train
Teacher: Generate a correct and concise answer for the question based on the words in the context. Teacher: Now, understand the problem? If you are still confused, see the following example: Context : Isaac Nicola Romero (1916 in Havana, Cuba -- 1997) was a prominent Cuban guitarist and one of the founders of the modern Cuban Guitar School. Question : What was Isaac Nicola's city of birth? Solution: Havana Reason: According to context Issac Nicola's city of birth is Havana. Hence this is a correct output. Now, solve this instance: Context : Power Rangers Time Force is an American television series and the ninth season of the Power Rangers franchise, based on the Super Sentai series Mirai Sentai Timeranger, running for 40 half-hour episodes from February to November 2001. Question : Which is the basis of Power Rangers Time Force? Student:
Mirai Sentai Timeranger
task1327_qa_zre_answer_generation_from_question
NIv2
fs_opt
2
test
Generate a correct and concise answer for the question based on the words in the context. Context : Tan Yuling (1920 -- 14 August 1942), born Tatara Yuling, was a concubine of China's last emperor Puyi. Question : What is Tan Yuling's spouse's name? Puyi Context : Karl-Wilhelm von Schlieben (30 October 1894 -- 18 June 1964) was a German officer in World War I and World War II. Question : Which war did Karl-Wilhelm von Schlieben participate in? World War I Context : ``How a Bill Becomes a Law'' is the third episode of the fifth season of the American comedy television series Parks and Recreation, and the 71st overall episode of the series. Question : Which series is How a Bill Becomes a Law apart of?
Parks and Recreation
task1327_qa_zre_answer_generation_from_question
NIv2
fs_opt
0
validation
You will be given a definition of a task first, then some input of the task. In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Sentence 1: This appears to be a group of Asian people cleaning and preparing food. Sentence 2: Some people are preparing a meal. Output:
The people are at the bowling alley.
task187_snli_entailment_to_contradiction_text_modification
NIv2
zs_opt
1
train
Given the task definition, example input & output, solve the new input case. In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Example: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had gone inside the store and now has fruit. Output: Tom had not been in the store. The given sentence contradicts sentence 1 (i.e. they can not be correct at the same time.) New input case for you: Sentence 1: A female swimmer coming up for air as she does the butterfly stroke. Sentence 2: The female is swimming. Output:
The female is playing basketball.
task187_snli_entailment_to_contradiction_text_modification
NIv2
fs_opt
1
train
Teacher: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Teacher: Now, understand the problem? If you are still confused, see the following example: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had gone inside the store and now has fruit. Solution: Tom had not been in the store. Reason: The given sentence contradicts sentence 1 (i.e. they can not be correct at the same time.) Now, solve this instance: Sentence 1: A group of football players from opposing teams are executing a play, one is on the ground in the background. Sentence 2: A group of people are playing football. Student:
A group of hockey players are sitting on the bench.
task187_snli_entailment_to_contradiction_text_modification
NIv2
fs_opt
2
train
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Example input: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had gone inside the store and now has fruit. Example output: Tom had not been in the store. Example explanation: The given sentence contradicts sentence 1 (i.e. they can not be correct at the same time.) Q: Sentence 1: Two men in black clothes at a meat market showing a red meat while workers in blue look on. Sentence 2: men inspect meat while others observe A:
Two people are examining fresh fruit and vegetables.
task187_snli_entailment_to_contradiction_text_modification
NIv2
fs_opt
3
train
Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Input: Sentence 1: Young women playing a intense game of lacrosse. Sentence 2: Young women play a sport together. Output:
The women are not playing a game.
task187_snli_entailment_to_contradiction_text_modification
NIv2
zs_opt
3
train
Teacher: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Teacher: Now, understand the problem? If you are still confused, see the following example: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had gone inside the store and now has fruit. Solution: Tom had not been in the store. Reason: The given sentence contradicts sentence 1 (i.e. they can not be correct at the same time.) Now, solve this instance: Sentence 1: At an outdoor event, one man is speaking into a megaphone while another man is holding the megaphone. Sentence 2: a man speaking into a megaphone outdoors Student:
A person is using a bobsled down the hill
task187_snli_entailment_to_contradiction_text_modification
NIv2
fs_opt
2
train
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task. In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had gone inside the store and now has fruit. Solution: Tom had not been in the store. Why? The given sentence contradicts sentence 1 (i.e. they can not be correct at the same time.) New input: Sentence 1: A pair of hands is shooting a black gun in the direction of trees. Sentence 2: Someone is shooting outside Solution:
the man is working in the field , picking cotton
task187_snli_entailment_to_contradiction_text_modification
NIv2
fs_opt
0
train
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Input: Consider Input: Sentence 1: A young group of children in uniforms talk to an elderly woman with a bag. Sentence 2: The young group of children are in uniforms Output: The people are sleep. Input: Consider Input: Sentence 1: A family sits around at Christmas time, some playing Jenga while others play with children. Sentence 2: Some people are playing Jenga. Output: A family is shooting fireworks. Input: Consider Input: Sentence 1: Boy does skateboard trick. Sentence 2: A child is skateboarding.
Output: A boy is on a bicycle.
task187_snli_entailment_to_contradiction_text_modification
NIv2
fs_opt
2
train
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. One example is below. Q: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had gone inside the store and now has fruit. A: Tom had not been in the store. Rationale: The given sentence contradicts sentence 1 (i.e. they can not be correct at the same time.) Q: Sentence 1: A couple in a parking lot. Sentence 2: A couple is walking together. A:
A couple is relaxing in the park.
task187_snli_entailment_to_contradiction_text_modification
NIv2
fs_opt
9
test
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Q: Sentence 1: People are standing and sitting at round tables in a large room. Sentence 2: People gathered in a room. A: People boarding a bus. **** Q: Sentence 1: A football player in purple is running the ball while another in white attempts to tackle him. Sentence 2: A football player in white tries to tackle a player in purple. A: A girl is sitting on her porch. **** Q: Sentence 1: Basketball players are reaching for the basketball as it flies through the air. Sentence 2: A group of basketball players are trying to get a rebound A:
Basketball flies with flies and touch players ****
task187_snli_entailment_to_contradiction_text_modification
NIv2
fs_opt
4
validation
The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. Example Input: missä on lähin vähintään 6 tähtiarvion saanut " mexican " ravintola ? Example Output: where is the nearest " mexican " restaurant with at least a 6 star review ? Example Input: näytä minulle kaikki 10 tähtiarvion saaneet " chinese " ravintolat 1 mailin säteellä . Example Output: show me all " chinese " restaurants with 10 star ratings within 1 miles . Example Input: etsi " cracker barrel " Example Output:
find " cracker barrel "
task254_spl_translation_fi_en
NIv2
fs_opt
3
train
The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. etsi " chipotle " search for " chipotle " näytä kaikki " italian " ravintolat . locate all " italian " restaurants . etsi 10 tähteä saaneita ravintoloita postinumerolla " 49503 " .
search for 10 star restaurants in the " 49503 " zip code .
task254_spl_translation_fi_en
NIv2
fs_opt
0
train
The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. Input: Consider Input: luettele " japanese " ravintolat. Output: list " japanese " restaurants . Input: Consider Input: näytä minulle kaikki vähintään 4 arviota saaneet " vegan " ravintolat . Output: show me a list of " vegan " restaurants with at least 4 reviews . Input: Consider Input: näytä minulle kaikki vähintään 4 arviota saaneet " vegan " ravintolat .
Output: show me a list of " vegan " restaurants with at least 4 reviews .
task254_spl_translation_fi_en
NIv2
fs_opt
2
train
You will be given a definition of a task first, then some input of the task. The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. hae " luby 's cafeteria ". Output:
search for " luby 's cafeteria " .
task254_spl_translation_fi_en
NIv2
zs_opt
1
train
The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. Q: mitä ravintoloita " mark " on arvostellut? A: what are the restaurants reviewed by " mark " ? **** Q: näytä minulle " italian "-ravintolat. A: show me " italian " restaurants . **** Q: anna ravintolan " jade buffet " arvostelut. A:
give me reviews for " jade buffet " . ****
task254_spl_translation_fi_en
NIv2
fs_opt
4
train
Teacher: The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. Teacher: Now, understand the problem? If you are still confused, see the following example: löytyykö läheltäni yhtään " italian " ravintolaa joka on saanut vähintään 1 tähden arvioita? Solution: are there any " italian " restaurants nearby with 1 star reviews ? Reason: The translation correctly preserves " italian " entity and is accurate Now, solve this instance: löydä kaikki ravintolat, joiden luokitus on korkeampi kuin 4 Student:
find all restaurants rated higher than 4
task254_spl_translation_fi_en
NIv2
fs_opt
2
train
The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. Example Input: voinko lukea lähimmän " italian " ravintolan kuvauksen ? Example Output: can i read the description of the closest " italian " restaurant ? Example Input: näytä lähimmän 10 tähteä saaneen ravintolan kuvaus . Example Output: show description of the closest 10 star restaurant . Example Input: etsi kaikki ravintolat jotka on arvosteltu yli 2 Example Output:
find all restaurants rated higher than 2
task254_spl_translation_fi_en
NIv2
fs_opt
3
train
The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. Input: Consider Input: löydä minulle " mod pizza ". Output: find " mod pizza " for me . Input: Consider Input: kuinka monta arviota " old town doughnuts " on saanut ? Output: how many reviews have been posted for " old town doughnuts " ? Input: Consider Input: voitko näyttää minulle " j dog " -ravintolan arvostelut?
Output: can you show me the ratings for " j dog " ?
task254_spl_translation_fi_en
NIv2
fs_opt
2
train
Q: The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. mikä on " mcdonald 's " ravintolan osoite kohteessa " parker road " ? A:
what 's the address of the " mcdonald 's " on " parker road " ?
task254_spl_translation_fi_en
NIv2
zs_opt
7
test
Instructions: The provided file includes inquiries about restaurants in Finnish, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. Input: löydä " mexican " ravintoloita. Output:
find " mexican " restaurants .
task254_spl_translation_fi_en
NIv2
zs_opt
3
validation
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Input: Consider Input: Sentence 1: Three children pull on a length of rope while adults and other children look on in the background. Sentence 2: Three children hold a snake and tease the adults who looked on in horror. Output: A group of grown ups watch three children play with some rope. Input: Consider Input: Sentence 1: A surly man pulls a piece of freshly baked bread from a stone oven. Sentence 2: the man is happy Output: The man is baking Input: Consider Input: Sentence 1: People are watching from the sidelines of an inner city foot race. Sentence 2: The man was sleeping.
Output: People are watching a race.
task186_snli_contradiction_to_entailment_text_modification
NIv2
fs_opt
2
train
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Input: Consider Input: Sentence 1: A man with a green star balloon standing to the side of the door of an ancient looking building Sentence 2: A man is putting out a fire. Output: A man is holding a balloon. Input: Consider Input: Sentence 1: Children watch a bicyclist perform on a tightrope. Sentence 2: The children are watching to clowns hit each other. Output: Children watch a bicyclist on a tightrope. Input: Consider Input: Sentence 1: A young man on his hands and knees painting a colorful sign on a parking lot. Sentence 2: a man reading a book quietly alone
Output: a man paints
task186_snli_contradiction_to_entailment_text_modification
NIv2
fs_opt
2
train
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Ex Input: Sentence 1: A woman in a white shirt and pink pants is standing behind a table laid out with cake, strawberries and punch. Sentence 2: A woman is eating the wedding cake. Ex Output: a woman stands by the refreshment table Ex Input: Sentence 1: A lady pushes a stroller, behind a child, riding a tricycle, while another child walks along side. Sentence 2: The lady was watching TV with her 2 children. Ex Output: A lady is with her children Ex Input: Sentence 1: A baseball batter in white pants and a black shirt attempting to hit a baseball with a catcher behind him and an umpire behind the catcher. Sentence 2: The people are playing football. Ex Output:
people play baseball
task186_snli_contradiction_to_entailment_text_modification
NIv2
fs_opt
1
train
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. One example is below. Q: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had not been in the store. A: Tom had gone inside the store and now has fruit. Rationale: Tom must have been inside the store to come out, and have fruit, so the altered sentence aggrees with sentence 1. Q: Sentence 1: A group of young volleyball players celebrate on the court. Sentence 2: A group of young basketball players celebrate on the court. A:
People celebrating a on volleyball court.
task186_snli_contradiction_to_entailment_text_modification
NIv2
fs_opt
9
train
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Q: Sentence 1: A man wearing blue sits on a chair in front of a brick building. Sentence 2: The giraffe stands near the building. A: The man is in blue. **** Q: Sentence 1: A man wearing black shorts is standing in front of a snow covered mountain. Sentence 2: A man sits in his office eyeing his new secretary. A: A man is outside. **** Q: Sentence 1: A marching band in red and white uniforms. Sentence 2: The marching band is wearing black uniforms. A:
The marching band is wearing uniforms. ****
task186_snli_contradiction_to_entailment_text_modification
NIv2
fs_opt
4
train
Detailed Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Problem:Sentence 1: Three young adults gaze at the approaching storm. Sentence 2: 3 people look at the sun Solution:
3 people look at the coming storm
task186_snli_contradiction_to_entailment_text_modification
NIv2
zs_opt
8
train
Detailed Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. See one example below: Problem: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had not been in the store. Solution: Tom had gone inside the store and now has fruit. Explanation: Tom must have been inside the store to come out, and have fruit, so the altered sentence aggrees with sentence 1. Problem: Sentence 1: a young skateboarder jumping a trick in the air. Sentence 2: The skateboarder walks home. Solution:
The trick is performed in the air.
task186_snli_contradiction_to_entailment_text_modification
NIv2
fs_opt
4
train
Teacher:In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Teacher: Now, understand the problem? Solve this instance: Sentence 1: A woman in a blue and brown parka with matching hat is in a snow-covered forest on either crosscountry skis or snowshoes, which are obscured by the ruts in the trail she is following. Sentence 2: A woman is sunbathing on the beach. Student:
The woman is outdoors.
task186_snli_contradiction_to_entailment_text_modification
NIv2
zs_opt
6
train
Definition: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Input: Sentence 1: A young girl in a pink dress with something in her hand. Sentence 2: A girl is throwing a stone. Output:
A girl is holding something.
task186_snli_contradiction_to_entailment_text_modification
NIv2
zs_opt
2
test
In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence. Sentence 1: Two guys installing tile in which is maybe a bathroom Sentence 2: The men are fighting each other.
The men are touching tile.
task186_snli_contradiction_to_entailment_text_modification
NIv2
zs_opt
0
validation
In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". Example: Sentence-1: I'm looking forward to it.<sep>Sentence-2: I did hear about the event next week . Example solution: Yes Example explanation: We need to check if the answer is yes or no based on the given sentence-1 and sentence-2. Both the sentences give the same meaning, and so the output is a yes. Problem: Sentence-1: I'm sure they're great people, let's meet up.<sep>Sentence-2: I want to meet of my friends .
Solution: Yes
task566_circa_classification
NIv2
fs_opt
5
train
In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". Sentence-1: I try to go to the gym a few times a week.<sep>Sentence-2: I am into fitness .
Yes
task566_circa_classification
NIv2
zs_opt
0
train
In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". Q: Sentence-1: Lollapalooza is my favorite event of the year.<sep>Sentence-2: I have ever been to a music festival . A:
Yes
task566_circa_classification
NIv2
zs_opt
4
train
TASK DEFINITION: In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". PROBLEM: Sentence-1: I'd rather go to a concert.<sep>Sentence-2: I have an interest in movies . SOLUTION: Yes PROBLEM: Sentence-1: I don't care for his music.",Sentence-2: "I am going to see Elton John 's farewell tour ." SOLUTION: No PROBLEM: Sentence-1: sometimes I am<sep>Sentence-2: I am happy . SOLUTION:
Yes
task566_circa_classification
NIv2
fs_opt
8
train
In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". Q: Sentence-1: I love to dance at live music shows.<sep>Sentence-2: I like to see live music . A:
Yes
task566_circa_classification
NIv2
zs_opt
4
train
Given the task definition and input, reply with output. In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". Sentence-1: I move often due to work.<sep>Sentence-2: This is somewhere .
Yes
task566_circa_classification
NIv2
zs_opt
5
train
In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". Q: Sentence-1: As long as there isn't any singing in it.<sep>Sentence-2: I would like to attend the play at the theater . A: Yes **** Q: Sentence-1: I'm afraid I have a limited palate.<sep>Sentence-2: I enjoy eating new foods . A: No **** Q: Sentence-1: I love local restaurants.<sep>Sentence-2: I am into trying a mom and pop burger place near me . A:
Yes ****
task566_circa_classification
NIv2
fs_opt
4
train
In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". Q: Sentence-1: If it isn't too expensive.<sep>Sentence-2: I am up for going to the museum tomorrow . A: Yes **** Q: Sentence-1: I work 5 days a week.<sep>Sentence-2: I am employed full-time . A: Yes **** Q: Sentence-1: I'm learning to knit.<sep>Sentence-2: I have been up to something new . A:
Yes ****
task566_circa_classification
NIv2
fs_opt
4
train
In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". Q: Sentence-1: It's me and my family.<sep>Sentence-2: I living alone . A: No **** Q: Sentence-1: I'd also choose spicy food over any other type.<sep>Sentence-2: I prefer spicy dishes . A: Yes **** Q: Sentence-1: I'm a homebody.<sep>Sentence-2: I love fast life . A:
Yes ****
task566_circa_classification
NIv2
fs_opt
4
test
In this task, you are given two sentences. Your task is to classify the given sentences as "Yes" if they have same meaning; otherwise, classify them as "No". Example: Sentence-1: I'm looking forward to it.<sep>Sentence-2: I did hear about the event next week . Example solution: Yes Example explanation: We need to check if the answer is yes or no based on the given sentence-1 and sentence-2. Both the sentences give the same meaning, and so the output is a yes. Problem: Sentence-1: I love watching films especially on the big screen.<sep>Sentence-2: I am into the cinema .
Solution: Yes
task566_circa_classification
NIv2
fs_opt
5
validation
Definition: You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input Input: ASSISTANT: What kind of movies to you like, and why do you like this type of movie? , USER: Let's see. I like action-adventure and I like those types of movies because I'm always on the edge of my seat and they're really exciting to watch. , ASSISTANT: Can you name a particular movie that you like? , USER: The Beach , ASSISTANT: Can you give me a couple of reasons why you like this movie? , USER: Yeah. It's kind of like action adventure with a little bit of mystery added in and throughout the movie you're just trying to figure out who's committing murders, and it's just super exciting and just a lot under watch and kind of, you know? While you're watching you're just of trying to figure everything out, classify_text: before the end of the movie comes Output:
USER
task925_coached_conv_pref_classifier
NIv2
zs_opt
2
train
Detailed Instructions: You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input Problem:ASSISTANT: What type of movies do you like? , USER: Comedies. , ASSISTANT: okay what do you like about comedies? , USER: That they make me happy when I don't feel like I have any other reason to be happy. They give distract. , ASSISTANT: Can you tell me the title of one of your favorite movies? , USER: White Chicks, classify_text: Can you say why you like that type of movie? Solution:
ASSISTANT
task925_coached_conv_pref_classifier
NIv2
zs_opt
8
train
Given the task definition and input, reply with output. You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input ASSISTANT: Hello, can you please name one of your favourite movie? , USER: One of my favorite movies is Remember the Titans. , ASSISTANT: Great! now. What is it about this type of movie that you like? , USER: I like it because it's a sports movie. , ASSISTANT: and what else other than being a sports movie? , USER: I like that, it's funny., classify_text: what else?
ASSISTANT
task925_coached_conv_pref_classifier
NIv2
zs_opt
5
train
Detailed Instructions: You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input Q: ASSISTANT: What kind of movies do you enjoy and why? , USER: I like the really like the thrillers, you know, stuff like Memento or you know, something that's got some twists and turns in it. Maybe it makes you think it's going to end one way and then ends the other. I like The Sixth Sense or that Gone Girl was pretty good, even though it was kind of , USER: It was kind of easy to tell it was going, but it was still still pretty good. Also trying to think of another one. , ASSISTANT: Is there a particular film you enjoy? , USER: Yeah, The Usual Suspects, because Mainly because I really When I watched it the first time, it's one of those movies that you can't really I mean, you can watch it more than once, but you The first time you watch, you won't know the twist, so it really kind of grabs you. And with that one, I really didn't have any clue. I mean, usually you might have some kind of inkling of what's going to happen, but with that movie to me, it just really kind of grabbed me, and I was like, man , USER: It left me kind of speechless at the end., classify_text: What did you like about that film? A:
ASSISTANT
task925_coached_conv_pref_classifier
NIv2
zs_opt
9
train
instruction: You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input question: ASSISTANT: What kind of movies to you like, and why do you like this type of movie? , USER: I like action adventure films because there's a lot going on, and keeps me in suspense, and they're fun to watch. , ASSISTANT: Can you name a particular movie that you like? , USER: Like True Lies , ASSISTANT: Can you give me a couple of reasons why you like this movie? , USER: Sure. It was a lot of action. You know, a lot of witty dialog, lot of stuff going on. You know, just a good plot, good story, very interesting., classify_text: Can you name a movie that you do not like? answer: ASSISTANT question: ASSISTANT: What kind of movies do you normally watch? , USER: science fiction , ASSISTANT: What do you like the most about Science Fiction movies? , USER: I enjoy the speculative aspects and the fantastical bits as well as the notion of satire and also advanced technology. , ASSISTANT: Have you seen Venom? , USER: No., classify_text: Have you seen Whiplash? answer: ASSISTANT question: ASSISTANT: Could you tell me about one of your favorite movies? , USER: One of my favorite movies is Wayne's World. , ASSISTANT: Would you care to elaborate about that genre? , USER: The genre is comedy. , ASSISTANT: And what about that do you like? , USER: I like the humorous aspect of it., classify_text: Ok thanks. How about a movie you really didn't like? answer:
ASSISTANT
task925_coached_conv_pref_classifier
NIv2
fs_opt
9
train
You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input Q: ASSISTANT: What type of movies do you like? , USER: I enjoy family, fantasy and mysteries. , ASSISTANT: why fantasy movies? , USER: I just like the fantasy part where you can enjoy watching something that is not common or doesn't really happen and the idea of that being able to happen one day. , ASSISTANT: What is one of your favorite movies? , USER: One of my favorite movies was something I watched as a child and it's still is one of my favorite movies The NeverEnding Story., classify_text: Why? A: ASSISTANT **** Q: ASSISTANT: What kinds of movies do you like? , USER: romance , ASSISTANT: Why do you like romance movies? , USER: Because they make you feel good. , ASSISTANT: Is there a romance movie you like? , USER: How to Lose a Guy in 10 Days, classify_text: and why did you like that movie? A: ASSISTANT **** Q: ASSISTANT: I'd like to discuss your movie preferences. , USER: I like musical movies. , USER: They transform me into a world that I didn't know existed, and it makes me peaceful, happy, and like I believe that I can do anything I want. , USER: The Wizard of Oz , ASSISTANT: what did you like about it? , USER: It made me believe in the ever-after in another word that I have just dreamed about., classify_text: I did not like scary movies like Screams. Scream was not one of my favorites. A:
USER ****
task925_coached_conv_pref_classifier
NIv2
fs_opt
4
train
You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input ASSISTANT: what kind of movies do you like? , USER: I like horror movies. , ASSISTANT: what do you like about horror movies? , USER: movie I liked a lot. , USER: I like Jason X. I like the movie Jason X. , ASSISTANT: what did you like about it?, classify_text: What I liked about Jason X was that
USER
task925_coached_conv_pref_classifier
NIv2
zs_opt
0
train
Detailed Instructions: You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input Problem:ASSISTANT: what type of movies do you like , USER: I like comedies. , ASSISTANT: is there any specific title that youre fond of , USER: I love , USER: What was it called? , ASSISTANT: What did you like about this movie?, classify_text: It was all great because to see all the girls going on a trip and sharing different experiences and seeing different personalities away from home, and it was just awesome. Solution:
USER
task925_coached_conv_pref_classifier
NIv2
zs_opt
8
train
You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input [EX Q]: ASSISTANT: What type of movies do you enjoy? , USER: I like sci-fi movies quite a bit. , ASSISTANT: What do you enjoy about them? , USER: It's an interesting take on the future and kind of seeing what people think the future will be like and it's just neat to see how people's brains were able to come up with ideas that might be realistic. , ASSISTANT: I can definitely see why people would be interested in that especially with that imaginative aspect , ASSISTANT: What movie from that genre do you enjoy?, classify_text: I haven't seen it in a while but I really liked Gattaca. [EX A]: USER [EX Q]: ASSISTANT: What kind of movies do you like? , USER: I like comedies and action movies. , ASSISTANT: Why's that? , USER: Because I like lighthearted movies. And I also like it when there are a lot of things going on when I'm watching a film. , ASSISTANT: I see. Why's that important to you? , USER: Well, I feel like I should be enjoying myself when participating in entertainment., classify_text: Okay. And what kind of movies do you dislike ? [EX A]: ASSISTANT [EX Q]: ASSISTANT: hello. Can you tell me, What type of movies do you like? , USER: I really like thriller movies. , ASSISTANT: OK. Great. Why do you like thrillers? , USER: They make you think through it all. , ASSISTANT: Can you tell me the title of one of your favorite movies? , USER: I really liked The Loft., classify_text: Ok. What is it about this type of movie that you like? [EX A]:
ASSISTANT
task925_coached_conv_pref_classifier
NIv2
fs_opt
6
test
Detailed Instructions: You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input See one example below: Problem: ASSISTANT: generally speaking what type of movies do you watch , USER: I like thrillers a lot. , ASSISTANT: thrillers? for example? , USER: Zodiac's one of my favorite movies. , USER: Zodiac the movie about a serial killer from the '60s or '70s, around there. , ASSISTANT: Zodiac? oh wow ok, what do you like about that movie, classify_text: And I just think serial killers, in general, are interesting, so the movie was really good. And it was just neat to see that world. Like it went really in-depth. It was like almost 3 hours long, so you got to really feel like you were a part of that world and time period. And see what the detectives and the police did and the investigators. Solution: USER Explanation: Based on last conversation in which the ASSISTANT ask's a question for which it waits for a reply from the "USER". We can classify this conversation as "USER" as it needs to respond for the given question. Problem: ASSISTANT: What types of movies do you usually see? , USER: I like cool movies. , ASSISTANT: What do you think is the best movie ever? , USER: I really enjoyed The Thing, John Carpenter's The Thing. , ASSISTANT: Nice. What was your favorite thing about it? , USER: I really enjoyed the special effects of the movie., classify_text: What else did you like about it? Solution:
ASSISTANT
task925_coached_conv_pref_classifier
NIv2
fs_opt
4
validation
Part 1. Definition In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. Part 2. Example Passage: I submitted the hit. The hit was approved, and then I was paid. Question: What happened after I submitted the hit? Events: ['submitted', 'approved', 'paid']. Answer: approved, paid Explanation: From the passage, we can infer that events approved and paid happened after the event submitted. Therefore, the answer to this question is "approved, paid". Part 3. Exercise Passage: While the life insurance association has the authority to work out the bail-out scheme, he said Hitachi and Nissan Motor might participate. "We cannot say that the Hitachi-Nissan group is entirely irrelevant, as they have been sending managers to Nissan Life," Fukuda said. Question: What did the association do in the past? Events: ['has', 'work', 'bail-out', 'said', 'participate', 'say', 'is', 'have', 'sending', 'said'] Answer:
task390_torque_text_span_selection
NIv2
fs_opt
7
train
In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. Example: Passage: I submitted the hit. The hit was approved, and then I was paid. Question: What happened after I submitted the hit? Events: ['submitted', 'approved', 'paid']. Example solution: approved, paid Example explanation: From the passage, we can infer that events approved and paid happened after the event submitted. Therefore, the answer to this question is "approved, paid". Problem: Passage: The defence minister also urged no further delay in the planned relocation of US bases to Pyeongtaek south of Seoul. The defence ministry said this week that South Korea would not be able to complete a major relocation of US military bases by 2008 as scheduled, due to protests by residents and a dispute over cost-sharing. Question: What happened before the defence ministry said anything? Events: ['urged', 'delay', 'relocation', 'said', 'be', 'relocation', 'protests', 'dispute']
Solution: urged
task390_torque_text_span_selection
NIv2
fs_opt
5
train
In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. Let me give you an example: Passage: I submitted the hit. The hit was approved, and then I was paid. Question: What happened after I submitted the hit? Events: ['submitted', 'approved', 'paid']. The answer to this example can be: approved, paid Here is why: From the passage, we can infer that events approved and paid happened after the event submitted. Therefore, the answer to this question is "approved, paid". OK. solve this: Passage: West German and French authorities have cleared Dresdner Bank AG's takeover of a majority stake in Banque Internationale de Placement (BIP), Dresdner Bank said. The approval, which had been expected, permits West Germany's second-largest bank to acquire shares of the French investment bank. Question: What needed to happen before the German bank acquired shares of the French bank? Events: ['cleared', 'takeover', 'said', 'approval', 'permits', 'acquire'] Answer:
cleared
task390_torque_text_span_selection
NIv2
fs_opt
8
train
Given the task definition, example input & output, solve the new input case. In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. Example: Passage: I submitted the hit. The hit was approved, and then I was paid. Question: What happened after I submitted the hit? Events: ['submitted', 'approved', 'paid']. Output: approved, paid From the passage, we can infer that events approved and paid happened after the event submitted. Therefore, the answer to this question is "approved, paid". New input case for you: Passage: NEW YORK: Covering as mourners gather to pay their respects to late soul legend James Brown, who will lie in state at Harlem's Apollo Theater from 1800 GMT. (AFPENTERTAINMENT-MUSIC-US-BROWN) Question: What will happen in the future? Events: ['Covering', 'gather', 'pay', 'lie'] Output:
lie
task390_torque_text_span_selection
NIv2
fs_opt
1
train
In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. One example is below. Q: Passage: I submitted the hit. The hit was approved, and then I was paid. Question: What happened after I submitted the hit? Events: ['submitted', 'approved', 'paid']. A: approved, paid Rationale: From the passage, we can infer that events approved and paid happened after the event submitted. Therefore, the answer to this question is "approved, paid". Q: Passage: For nearly forty years, the United States has said categorically it would not tolerate totalitarian rule in its own backyard. It is the US economic and political embargo which has kept Cuba in a box. Question: What did the United States not do after totalitarian rule came to Cuba? Events: ['said', 'tolerate', 'rule', 'embargo', 'kept'] A:
tolerate
task390_torque_text_span_selection
NIv2
fs_opt
9
train
In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. Q: Passage: "The BoJ may need to confirm first that consumer spending has accelerated before hiking rates," said NLI Research Institute senior economist Taro Saito, who is looking at a rate increase either in January or February. The market had widely expected the decision after the mixed economic data, including just 0.1 percent year-on-year growth in core consumer prices. Question: What did the market do before the 0.1 percent growth? Events: ['need', 'confirm', 'spending', 'accelerated', 'hiking', 'said', 'looking', 'increase', 'expected', 'decision', 'growth'] A: **** Q: Passage: Spokesman Yuri Gremitskikh said the first group of 230 evacuees was assembling in Baghdad today, but evacuation plans were hampered by desert heat and lack of transportation. Nearly 9,000 Soviets were among the hundreds of thousands of foreigners trapped in Iraq and Kuwait. Question: What will happen in the future? Events: ['said', 'was', 'assembling', 'hampered', 'lack', 'were', 'among', 'trapped'] A: trapped **** Q: Passage: Spokesman Yuri Gremitskikh said the first group of 230 evacuees was assembling in Baghdad today, but evacuation plans were hampered by desert heat and lack of transportation. Nearly 9,000 Soviets were among the hundreds of thousands of foreigners trapped in Iraq and Kuwait. Question: what happened after the evacuees were assembling? Events: ['said', 'was', 'assembling', 'hampered', 'lack', 'were', 'among', 'trapped'] A:
hampered ****
task390_torque_text_span_selection
NIv2
fs_opt
4
train
Part 1. Definition In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. Part 2. Example Passage: I submitted the hit. The hit was approved, and then I was paid. Question: What happened after I submitted the hit? Events: ['submitted', 'approved', 'paid']. Answer: approved, paid Explanation: From the passage, we can infer that events approved and paid happened after the event submitted. Therefore, the answer to this question is "approved, paid". Part 3. Exercise Passage: Flintoff had said he hoped to remain captain for the one-day series on Monday, just after the third Test loss to Australia. "If the job is available, of course I will," Flintoff said when asked if he would make himself available to captain in the one-dayers. Question: What will happen in the future? Events: ['said', 'hoped', 'remain', 'series', 'loss', 'is', 'will', 'said', 'asked', 'make', 'captain', 'one-dayers'] Answer:
series
task390_torque_text_span_selection
NIv2
fs_opt
7
train
Detailed Instructions: In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. Problem:Passage: There are fears that ash and acid rain will continue to fall on homes and food crops, leading to the contamination of water supplies and respiratory problems for inhabitants. The Vanuatu government has not declared a state of emergency but has taken precautions in case the eruptions become worse. Question: What has not happened after ash and acid rain started falling? Events: ['are', 'continue', 'fall', 'leading', 'declared', 'taken', 'become', 'eruptions'] Solution:
declared
task390_torque_text_span_selection
NIv2
zs_opt
8
train
Detailed Instructions: In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. Q: Passage: He called U.S. soldiers massing in Saudi Arabia the real occupiers in the Persian Gulf. Replied State Department deputy spokesman Richard Boucher, ``We haven't really analyzed the statement in detail but it appears to be just another example of his outlandish rhetoric and his attempts to distort the truth. Question: What happened before Richard Boucher replied? Events: ['massing', 'Replied', 'analyzed', 'appears', 'statement', 'attempts', 'distort', 'called'] A:
called
task390_torque_text_span_selection
NIv2
zs_opt
9
test
Teacher: In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty. Teacher: Now, understand the problem? If you are still confused, see the following example: Passage: I submitted the hit. The hit was approved, and then I was paid. Question: What happened after I submitted the hit? Events: ['submitted', 'approved', 'paid']. Solution: approved, paid Reason: From the passage, we can infer that events approved and paid happened after the event submitted. Therefore, the answer to this question is "approved, paid". Now, solve this instance: Passage: Rajapakse in his election campaign was critical of the Norwegian-backed peace process with the Tiger rebels, which he claimed was giving in too much to the Tigers and the forces have been humiliated by it. The Sri Lankan President said in his address that despite action against the Tiger rebels in the battle fields of north and east, the rights of the peace-loving Tamil people must be safeguarded. Question: What will happen in the future? Events: ['campaign', 'critical', 'Norwegian-backed', 'process', 'with', 'claimed', 'giving', 'humiliated', 'action', 'safeguarded'] Student:
task390_torque_text_span_selection
NIv2
fs_opt
2
validation