prompt
stringlengths 50
14.7k
| response
stringlengths 1
3.54k
|
|---|---|
Given the task definition, example input & output, solve the new input case.
In this task, you will be given sentences in which your task is to recognize the name of the drug or medicine. Drugs are substances that change a person's mental or physical state. They can affect how your brain works, how you feel and behave, your understanding, and your senses. Although there might be several correct answers, you need to write one of them.
Example: Acute pain was observed after taking MTX
Output: MTX
MTX is a medicine which has been mentioned here, and hence the name should be tagged.
New input case for you: A case is presented of a patient who experienced benzodiazepine withdrawal symptoms on discontinuation of nefazodone, an antidepressant that inhibits the cytochrome P450 3A4 isoenzyme.
Output: | nefazodone |
Teacher:In this task, you are given a country name and you need to return the region of the world map that the country is located in. The possible regions that are considered valid answers are: Caribbean, Southern Europe, Eastern Europe, Western Europe, South America, North America, Central America, Antarctica, Australia and New Zealand, Central Africa, Northern Africa, Eastern Africa, Western Africa, Southern Africa, Eastern Asia, Southern and Central Asia, Southeast Asia, Middle East, Melanesia, Polynesia, British Isles, Micronesia, Nordic Countries, Baltic Countries.
Teacher: Now, understand the problem? Solve this instance: United Kingdom
Student: | British Isles |
Given the task definition and input, reply with output. In this task, you are given commands (in terms of logical operations) and natural interpretation of the given command to select relevant rows from the given table. Your job is to generate a label "yes" if the interpretation is appropriate for the command, otherwise generate label "no".
Here are the definitions of logical operators:
1. count: returns the number of rows in the view.
2. only: returns whether there is exactly one row in the view.
3. hop: returns the value under the header column of the row.
4. and: returns the boolean operation result of two arguments.
5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column.
6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column.
7. argmax/argmin: returns the row with the max/min value in header column.
8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column.
9. eq/not_eq: returns if the two arguments are equal.
10. round_eq: returns if the two arguments are roughly equal under certain tolerance.
11. greater/less: returns if the first argument is greater/less than the second argument.
12. diff: returns the difference between two arguments.
13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument.
14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument.
15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument.
16. filter_all: returns the view itself for the case of describing the whole table
17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument.
18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument.
19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument.
20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument.
21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument.
22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.
Command: round_eq { avg { all_rows ; result } ; 3rd place }, interpretation: the average of the result record of all rows is 3rd place .
| yes |
Detailed Instructions: In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.
Q: Sentence: 'stir fried noodles with meat and chopped broccoli'. Is 'noodles' the longest word in the sentence?
A: | No |
Read the given story and classify it as 'imagined', 'recalled', or 'retold'. If a story is imagined, the person who wrote the story is making it up, pretending they experienced it. If a story is recalled, the person who wrote the story really experienced it and is recalling it from memory. If a story is retold, it is a real memory like the 'recalled' stories, but written down much later after previously writing a 'recalled' story about the same events. So, recalled stories and retold stories will be fairly similar, in that they both were real experiences for the writer. Imagined stories have a more linear flow and contain more commonsense knowledge, whereas recalled stories are less connected and contain more specific concrete events. Additionally, higher levels of self reference are found in imagined stories. Between recalled and retold stories, retold stories flow significantly more linearly than recalled stories, and retold stories are significantly higher in scores for cognitive processes and positive tone.
One example is below.
Q: Concerts are my most favorite thing, and my boyfriend knew it. That's why, for our anniversary, he got me tickets to see my favorite artist. Not only that, but the tickets were for an outdoor show, which I love much more than being in a crowded stadium. Since he knew I was such a big fan of music, he got tickets for himself, and even a couple of my friends. He is so incredibly nice and considerate to me and what I like to do. I will always remember this event and I will always cherish him. On the day of the concert, I got ready, and he picked me up and we went out to a restaurant beforehand. He is so incredibly romantic. He knew exactly where to take me without asking. We ate, laughed, and had a wonderful dinner date before the big event. We arrived at the concert and the music was so incredibly beautiful. I loved every minute of it. My friends, boyfriend, and I all sat down next to each other. As the music was slowly dying down, I found us all getting lost just staring at the stars. It was such an incredibly unforgettable and beautiful night.
A: imagined
Rationale: This is a good example because it really was an imagined story. The attributes that should tip you off are that the story is light on concrete events (they describe things in broad terms such as going to a restaurant and being at the stadium, but nothing specific about who was exactly where and anything specifically notable someone said or did) and heavy on references to the writer themselves and their internal feelings (they frequently repeat how much they loved it, how romantic they felt, how they cherished the night, etc). It's also very linear and structured, pointing to this being an imagined story. Additionally, the events and feelings described seem a little romanticized or idealized beyond what is usually a realistic circumstance.
Q: If we had known, we would have listened to friends and moved house. A month ago, when there were warnings that people should leave the area because T.S. Imelda was coming, a cyclone that was predicted to hit our area in Texas, we thought the storm was minor. We were even unconcerned when it was reported in the media that the storm had been upgraded to a tropical storm. We thought that after Harvey, we were secure because we had carried out major constructions on our house. Then one morning, out of nowhere, our house was flooded. It was unbelievable. It took us unawares. There was no news about it happening that morning. We were practically unaware that that morning was going to be the worst in our entire lives. I woke my wife in bed and she screamed. It was a scary experience. The first thought that came to my mind was that this was extremely tough on us after Harvey. One month ago, we had a beautiful home but right now, we are struggling to keep it in good shape. We are presently staying with friends because the house is said to be in uninhabitable conditions. The insurance is coming on slowly and the process is tough not after Harvey. If we had foreseen this, we would have been more prepared for Tropical Storm Imelda.
A: | imagined |
Detailed Instructions: Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.
Problem:I_TURN_RIGHT I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_TURN_RIGHT I_LOOK I_TURN_LEFT I_TURN_LEFT I_RUN I_TURN_LEFT I_TURN_LEFT I_RUN
Solution: | run opposite left twice after look opposite right thrice |
Instructions: In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.
Input: ['z', 7145, 'v', '2185', 'w', '9983', 'Q', '9747', 'k', 'q', 'c', 'F'], ['T', 'N', 'v', '2185', 'w', '9983', 'Q', '9747', 'k', 'q', 'Z', 7569, 'L', 'Z', 'H', 'y', 9547, 5693]
Output: | v, 2185, w, 9983, Q, 9747, k, q |
Given the task definition and input, reply with output. Given a sentence in Vietnamese, generate a new Vietnamese sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.
Nếu em muốn tổ chức tiệc thì em nên tổ chức tiệc.
| Nếu con muốn có một bữa tiệc thì con nên gặp khách. |
Given the task definition, example input & output, solve the new input case.
In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.
Example: ['q', '31', 'a', 'd', '53', '85', 'p', '77']
Output: 1, 3, 5, 7, 8
Here, the numbers in the list are '31', '53', '85' and '77', and the unique digits used in the list are '1, 3, 5, 7, 8' in ascending order.
New input case for you: ['w', 'n']
Output: | -1 |
Given a prompt and two completions from a language model, select the completion that has the most similar style to the prompt. Style is defined as the tone, word choice, grammar, and sentence structure throughout the prompt-completion pair. If a prompt is colloquial, then the completion should also be colloquial, as opposed to a completion that is encyclopedic or overly formal. Generate either Completion A or Completion B.
--------
Question: Prompt: Lez, you're a jerk ass! Well, you never told
Completion A: anyone. I don't blame you. I can't give this to anybody. They're the worst people you know. I'm sorry. Don't
Completion B: me where you lived, and I thought that you were one of those weirdo homeless people that didn't want anything to do with you. But yo
Answer: Completion B
Question: Prompt: I'm rolling on the floor laughing my fucking ass off. This kid is screaming, \"Do your dance on my dick. Oh,
Completion A: I didn't mean to. I'm gonna hit that wall now. I'll make the next song a great one. If you've got that,
Completion B: and my dick is gonna feel this much better in your pussy. Oh! I'm gonna fill your pussy with my cum. And, oh my Go
Answer: Completion B
Question: Prompt: Don't let me find out that bitches on Twitter are trash
Completion A: talking Trump. That's fine, I'll stay away. I'm waiting for Trump to do something of consequence, like his ban on immigration
Completion B: ! You‖re right, it's not worth that much. I'm sure you'd find a much more effective way to engage wit
Answer: | Completion A
|
Teacher: Given a sentence in Korean, provide an equivalent paraphrased translation in Spanish that retains the same meaning both through the translation and the paraphrase.
Teacher: Now, understand the problem? If you are still confused, see the following example:
1975 년부터 76 년까지 NBA 시즌은 전국 농구 협회 (National Basketball Association)의 30 번째 시즌이었다.
Solution: La temporada 1975 - 76 de la Asociación Nacional de Baloncesto fue la temporada 30 de la NBA.
Reason: This is a correct and accurate translation from Korean to Spanish because the translated paraphrase retains the main message that between the years 1975-1976, the 30th NBA season occurred.
Now, solve this instance: 2016 년 2 월, Daniel Pollack은 아르헨티나가 Paul Singer와 합의에 이르렀다 고 발표했습니다.
Student: | Daniel Pollack anunció en febrero de 2016 que Argentina había llegado a un acuerdo con Paul Singer. |
Paraphrase the given questions to have different wording. Your paraphrased questions should have the same answer as the original question. Try to change the sentence as much as possible using synonyms and/or rearranging the structure of the sentence. 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 paraphrasing, this keyword should also be used the same way. Do not write questions that compare or involve multiple domains. Do not write open-ended or subjective questions (e.g., questions that can be answered differently by different people.) Make your questions specific and concrete. Your question should have the same type of answer as the original question(e.g., if the question is extractive, the paraphrased question should be extractive as well.)
Ex Input:
What did this president major in during their college studies?
Ex Output:
What was the area of focus of this president during their years of higher education?
Ex Input:
Does this dog breed prefer colder climates?
Ex Output:
Is this dog breed better suited for cold environments?
Ex Input:
Was this president born on the east coast?
Ex Output:
| Is this president from an eastern u.s. state that touches the ocean?
|
In this task, you are given a string with unique characters in it and you need to return the character from the string which has the maximum ASCII value. ASCII stands for American Standard Code For Information Interchange and It assigns a unique number to each character. The characters [a - z] have an ASCII range of 97-122 and [A-Z] have an ASCII range of 65-90 respectively.
--------
Question: sEhCOzfFbamXMgpLBiTr
Answer: z
Question: rzKaDEefwXo
Answer: z
Question: xzFWjwHutyMGdZvENilf
Answer: | z
|
Instructions: In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.
Input: Sentence: 'the president of the united states tightens another mans tie'. Is 'states' the longest word in the sentence?
Output: | No |
In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.
Input: Consider Input: prprorproor
Output: rprorpr
Input: Consider Input: tttcccoctoo
Output: ttt
Input: Consider Input: zzzzzdzdzzzzddd
| Output: zzzzdzdzzzz
|
The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the uv-part strategy, otherwise output No. uv-part is a selfish negotiation strategy. It is used to undermine the requirements of the opponent. For instance, suggesting that the opponent would not need more firewood since they already have the basic supplies or a suggestion that there might be a store near the campsite where the opponent can get the supplies instead.
Let me give you an example: Context: 'Well maybe we can work something out between us. Our food and water was in the bags they loss so I really need those. Do you think you could make do with 1 food and some water?' 'I really need 2 foods. I can do with 1 water or if you are in a giving mood then maybe I can have 2 waters?' 'Looks like we both really need the food. If you get 2 food I would need 1 food, 2 water and 3 firewood. '
Utterance: 'Since you will get all the fire would do you think I could have 2 foods and 2 waters. You would get 1 food, 1 water, and 3 firewood. You seem like you are a great outdoor person that I would think you would be able to catch some fish to cook with the firewood.'
The answer to this example can be: Yes
Here is why: Correct. The participant tries to undermine their opponent's needs by mentioning that the opponent can just fish for food.
OK. solve this:
Context: 'That's fair, but I have wiggle room on the water, how about I take two food, two firewood and you take 3 water, 1 food, 1 firewood?' 'Is there anyway you will go with that I get two firewood? I need food the most but since you get most of that can I get most of the firewood? So 1 food, 2 firewood, and 2 water for me?' 'You drive a hard bargain. I could really use that firewood. It's going to get cold tonight and these sleeping bags are not worth the price I paid ;)'
Utterance: 'Haha, I know but I am in the same situation! ☹️ and since I am getting less food I feel like it is fair I get on more firewood since I truly need that 🙂'
Answer: | Yes |
Part 1. Definition
In this task, you are given a list of integers. You need to find the median of the list of integers and return that as the output. The median is the middle value in the list of numbers such that half of the elements are less than the median and the other half of elements are greater than the median.
Part 2. Example
[149, 403, 272, 453, 472, 499, 419, 277, 411, 252, 48, 359, 351, 147, 298, 61, 114, 178, 250, 34, 400, 417, 184, 326, 96]
Answer: 277
Explanation: 277 is the median of the input list.
Part 3. Exercise
[163, 394, 397, 442, 416, 69, 283, 144, 395, 154, 422, 43, 298, 229, 130, 294, 15, 405, 76, 263, 374, 240, 379, 197, 199]
Answer: | 263 |
instruction:
In this task you will be given two lists of numbers and you need to calculate the intersection between these two lists. The intersection between two lists is another list where every element is common between the two original lists. If there are no elements in the intersection, answer with an empty list. Your list of numbers must be inside brackets. Sort the numbers in your answer in an ascending order, that is, no matter what the order of the numbers in the lists is, you should put them in your answer in an ascending order.
question:
[2, 6, 3, 10, 10] , [8, 4, 7, 7, 1]
answer:
[]
question:
[9, 8, 2, 3, 6] , [8, 4, 8, 4, 7]
answer:
[8]
question:
[4, 9, 2, 1, 9, 3, 3, 8, 6] , [5, 3, 3, 6, 9, 9, 1, 8, 3]
answer:
| [1, 3, 6, 8, 9]
|
In this task, you will be presented with a question in Dutch language, and you have to write the location names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Identifier used for the location name - LOC. . There can be instances with no location name entity, then return 'None'.
Wüst ( Dui / Festina ) de 102,6 km in 2u28:10 -- 2 .
Dui: B-LOC
Ze zijn moe en uitgeput .
None
Bij winstparticipatie wordt een deel van het werknemersinkomen van te veel arbitraire beslissingen afhankelijk gemaakt .
| None
|
This task is about using the specified sentence and converting the sentence to Resource Description Framework (RDF) triplets of the form (subject, predicate object). The RDF triplets generated must be such that the triplets accurately capture the structure and semantics of the input sentence. The input is a sentence and the output is a list of triplets of the form [subject, predicate, object] that capture the relationships present in the sentence. When a sentence has more than 1 RDF triplet possible, the output must contain all of them.
Q: The Japanese Grand Prix in Motegi took place on September 28th.
A: [['Japanese Grand Prix', 'CIRCUIT', 'Motegi'], ['Japanese Grand Prix', 'DATE', '28 September']]
****
Q: When 11:40:26 is the time (utc) km (mi is the depth.
A: [['11:40:26', 'DEPTH', 'km (mi)']]
****
Q: Tony Estanguet competed in the men's slalom C-1 event in canoeing.
A: | [['Tony Estanguet', 'SPORT', 'Canoeing'], ['Canoeing', 'EVENT', "Men's slalom C-1"]]
****
|
Given the sentence, generate "yes, and" response. "Yes, and" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated ("Yes") and then expand on that line of thought or context ("and..."). 1 In short, a "Yes, and" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a "Yes, and" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'.
Forgive me, Ma'am. What's your name?
Murnice. My mother was going to call me Bernice, but she was humming when they got the gift certificate, I mean birth certificate.
I'm going to miss the crap out of you. I know I said some mean things when I found out you got into to Harvard and I'm going to stay here and work at the plant. But it's just because I was jealous.
I knew that. And I know I said mean things back to you because I am going to Harvard and you are staying here at the plant. But that's just because I was mad that you said those things to me.
I've been sent to your time, present day I guess, to fix a wrinkle in time that has caused a rupture that has allowed a woman who's not in scripture at all to exist in the garden of Eden. There's a weird, messy, divorce-like situation.
| This is very complex sounding, but it's right up my alley. I'm a scientist and I love time shit.
|
In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.
Ex Input:
['7', 'q', '201', 'p', '369', 'a', 'g', '429', 'i', 'g', '329', '295', '203']
Ex Output:
0, 1, 2, 3, 4, 5, 6, 7, 9
Ex Input:
['213', '51', '31', 'n', '89', '113', '315', '195', 'd', 'x', '105', '217', '295']
Ex Output:
0, 1, 2, 3, 5, 7, 8, 9
Ex Input:
['243', 'p']
Ex Output:
| 2, 3, 4
|
Part 1. Definition
You are given first 5 messages from a series of message exchanges between 2 persons playing the game of Diplomacy which is an American strategic board game. You need to generate the next message. The message should be generated such that it fits the context seen so far. Avoid the text that is (i) tangent to the context, (ii) repeats the context.
Part 2. Example
['Heyyyy Turkey', 'Whatcha thinking re: start of the game?', "It kind of depends. I'll probably want to stop Russia from advancing south", "I'm kind of afraid of Austria and Russia teaming together on me", 'I mean if that happens you’re donezos']
Answer: What vibes are you getting from each of them?
Explanation: The message fits the context as it asks for the vibes of 2 of them which refers to 2 countries: Austria and Russia in the second last message. Thus it is a positive example.
Part 3. Exercise
['Hey France 😁. I would like to suggest an alliance between the two of us, against Germany. In my opinion a England-France alliance is super powerful, especially if we can trust each other. Germany has reached out to me about an alliance to attack you, but franly I think France as a country is a much more powerful ally.To start I suggest we have the English Channel as a DMZ and coordinate and attack on Germany. Anyways good luck and have fun!', "Dear England,\nI completely agree that the French-English alliance can be quite powerful. Naturally, the main sticking point early on is whether we can trust each other to demilitarize the Channel.\nOn my end, I have little reason to go there unless I distrust you. I plan to go to Mid-Atlantic, which would allow me to move to Spain (south coast) and establish an early presence in the Mediterranean. Will also aim to get into Burgundy, where I can potentially support you into Belgium.\nMy suggestion is that you open with:\nF Edinburgh - Norwegian Sea\nF London - North Sea \nA Liverpool - Yorkshire\nThis guarrenteed you a build in Norway even if Russia moves A Moscow north, while potentially letting you convoy into Belgium. And you can be safe in the knowledge that either A Yorkshire or F North Sea can cover London in the event that I don't keep my word.\nLet me know your thoughts. Good luck to you as well!", 'Sounds good!', 'How are your relations with Germany?', 'Getting into burgundy would be great. I’ll work some magic with Germany and try to get them to not move there.']
Answer: | Relations with Germany are not outright hostile, but it's a little tense. Bounce in Burgundy is about what could be expected.
Since they moved to Holland in Spring, you'll need to talk to them regarding the Belgium question. But they can probably be brought around. I'll move to Burgundy again, but probably expecting another bounce |
We would like you to classify each of the following sets of argument pairs (discussing Gay Marriage) into either SIMILAR or NOT SIMILAR. A pair of arguments is considered SIMILAR if the arguments are about the same FACET (making the same argument), and is considered NOT SIMILAR if they do not have the same FACET. A FACET is a low level issue that often reoccurs in many arguments in support of the author's stance or in attacking the other author's position.
One example: Sent1: Many social conservatives argue that benefits are provided to married couples because, in turn, married couples benefit society.
Sent2: We give married couples marriage benefits TO STRENGTHEN the marriage, because marriage STRENGTHENS society.
Solution is here: Similar
Explanation: Both arguments argue that married couples can benefit the society.
Now, solve this: Sent1: For example, if a state Congress passes a bill that grants additional benefits to marriages and civil unions, a governor could simply line-item veto the benefit to civil unions, which then means that the benefits would apply only to marriage.
Sent2: Marriage is privilege not a right, because not every heterosexual couple even gets granted the right to marry... the state has a right to regulate what impacts the welfare of the union as whole.
Solution: | Not similar |
Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
['so', 'you', 'may', 'have', 'heard', 'of', "Tourette's", 'or', "Tourette's", 'syndrome', 'before', 'and', "it's", 'possible', 'that', 'when', 'you', 'think', 'about', "Tourette's", 'you', 'might', 'picture', "what's", 'been', 'kind', 'of', 'popularized', 'in', 'TV', 'shows', 'and', 'movies', 'which', 'is', 'that', 'people', 'with', "Tourette's", 'have', 'these', 'kind', 'of', 'verbal', 'outbursts', 'and', 'while', 'this', 'is', 'possible', 'in', 'someone', 'with', "Tourette's", 'this', 'popularized', 'image', 'of', "Tourette's", 'is', 'actually', 'not', 'all', 'that', 'common', 'so', 'if', 'this', "isn't", 'exactly', 'what', "Tourette's", 'is', 'always', 'like', 'then', 'what', 'is', "Tourette's", 'well', "Tourette's", 'is', 'a', 'disorder', 'that', 'causes', 'the', 'person', 'to', 'make', 'sudden', 'really', 'brief', 'unwanted', 'movements', 'and', 'sounds', 'and', 'just', 'before'] | ['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'CASE_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF'] |
Detailed Instructions: In this task, you will be presented with a question in Dutch language, and you have to write the part-of-speech tag for each word and punctuation in the question. Here is the list of part-of-speech tags used in this task: Adj: Adjective, Adv: Adverb, Art: Article, Conj: Conjunction, Int: Interjection, N: Noun, V: Verb, Num: Number, Misc: Miscellaneous, Pron: Pronoun, Prep: Preposition, Punc: Punctuation.
Problem:" Omdat de werking van het gen bij varkens en mensen zo sterk gelijkloopt , hopen we dat we het ook kunnen gebruiken om het type diabetes te behandelen dat bij oudere mensen voorkomt .
Solution: | Punc Conj Art N Prep Art N Prep N Conj N Adv Adj V Punc V Pron Pron Pron Pron Adv V V Conj Art N N Prep V Conj Prep Adj N V Punc |
TASK DEFINITION: In this task you will break down a question into the basic steps required to answer it.
A question decomposition is a numbered list of operations that must be performed to answer the original question. Imagine explaining your question to a friendly droid by listing each action it should take in order for the question to be answered. Each step in our decomposition should refer to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.)
Here are the list of step templates and their description:
Select: A select step is used to return a set of objects. There are no references to previous steps in a select step. template: Return [attributes]
Filter: A filter step is used to return results from a previous step to which a certain condition applies. template: Return [#step] [condition]
Project: A project step should return certain attributes of the results of a previous step. template: Return [attributes] of [#step]
Aggregate: An aggregate step returns an aggregator function applied on a step's result. template: Return the [aggregator] of [#step].
Group: A group step is an aggregator applied on attributes. template: Return the [aggregator] of [#step] for each [attribute]
Superlative: A superlative step is used to return the result with a highest/lowest attribute among other results. template: Return [#step1] [where] [#step2] [is] [highest / lowest]
Comparative: A comparative step is used when we need to compare an attribute with a number to filter results. template: Return [#step1] [where] [#step2] [comparator] [number]
Union: A union step is used to return results of two steps together. template: Return [#step1] [or / ,] [#step2]
Intersection: An intersection step returns the result that two steps have in common. template: Return [attribute] of both [#step1] and [#step2]
Discard: A discard step returns result of a step and excludes result of another step from it. template: Return [#step1] besides [#step2]
Sort: A sort returns result of another step in a specific order. template: Return [#step1] [ordered / sorted by] [#step2]
Is true: An is true step checks a condition on another result and returns a true or false. template: Return [is / if] [condition]
Arithmetic: An arithmatic step operates an arithmatic operation on one or more steps. template: Return the [arithmetic op.] of [#step1] [and] [#step2].
PROBLEM: question: If an image shows a burger next to slender french fries on a white paper in a container.
SOLUTION: #1 return burger
#2 return french fries
#3 return #2 that are slender
#4 return paper
#5 return #4 that is white
#6 return container
#7 return #1 next to #3
#8 return #7 on #5
#9 return #8 in #6
#10 return if #9 is in an image
PROBLEM: question: Which were there less of, English speakers or Spanish speakers?
SOLUTION: #1 return English speakers
#2 return Spanish speakers
#3 return number of #1
#4 return number of #2
#5 return which is less of #3 , #4
PROBLEM: question: How many more millions of people living in the EU we're born in Germany than in France?
SOLUTION: | #1 return people living in the EU
#2 return millions of people born in Germany of #1
#3 return millions of people born in France of #1
#4 return the difference of #2 and #3
|
Read the given story and classify it as 'imagined', 'recalled', or 'retold'. If a story is imagined, the person who wrote the story is making it up, pretending they experienced it. If a story is recalled, the person who wrote the story really experienced it and is recalling it from memory. If a story is retold, it is a real memory like the 'recalled' stories, but written down much later after previously writing a 'recalled' story about the same events. So, recalled stories and retold stories will be fairly similar, in that they both were real experiences for the writer. Imagined stories have a more linear flow and contain more commonsense knowledge, whereas recalled stories are less connected and contain more specific concrete events. Additionally, higher levels of self reference are found in imagined stories. Between recalled and retold stories, retold stories flow significantly more linearly than recalled stories, and retold stories are significantly higher in scores for cognitive processes and positive tone.
Q: My friend lost his father to cancer not too long ago. His father was very involved in the community, and was almost like a second father to us. It was incredibly hard to watch my friend loose someone so important to him. We all used to play a gold tournament every summer to support the cancer foundation. We haven't played the tournament since his fathers death. We decided it would be a good way to honor his life, by playing another tournament this summer. We all got ready to go, and the mood was kind of heavy. When we arrived, my friend seemed very sad. I attempted to lighten the mood by telling everyone a funny story about my friends father. We all shared some laughs and shared some more favorite memory's of his father. We ended up raising a lot of money for the organization. I think this trip helped with my friends grieving a lot. We decided to do this tournament every year. I am glad I got to share memories with my friends. I can't wait to play next summer.
A: imagined
****
Q: Five months ago, at the age of 63, i retired. This was an extremely important event; something i had looked forward to for quite a long time. After working in social service fields for approximately thirty years i was definitely "burned out." I had been a caseworker at the local Department of Social Services for a little over fourteen years. Then i spent approximately the same amount of time as a counselor working at a non profit agency. There are some who believe that this field of employment; working with all types of people who need a variety of services, is the number one field for burnout. whether or not this is true, i can honestly say that when i had the chance to retire, i knew it was the right time. The fact is that i had planned on working until i was 65 but i really needed to "get out." I had lost a lot of my patience; little things were beginning to annoy me, and worst of all i didn't feel as if i was giving the clients my best efforts. I can truly say that i am now the happiest I have ever been. Not only am i retired, but i spend four days a week with my wonderful two year old granddaughter. My wife runs a small day care center here in our house, so Kinsley comes over here four days a week and there is no way i can describe how much I adore her. She is our first grandchild; i had no idea how much i was going to enjoy my time with her. She seems to learn something new almost every day. The fact that i am retired means that i am on my own schedule and can spend as much time with Kinsley as i want. Things are so good with my life right now that it's almost too good to be true. What made my retirement so emotional was that i knew it was something I really needed emotionally. I knew it was the right time to stop working. Spending so much time now with my granddaughter makes it all even better.
A: recalled
****
Q: At the end of May 2019 myself and my family went on Vacation to the Smoky Mountains. It was the first time my children had ever been. We took them to DollyWood and my 8 year old daughter was finally able to ride the "big rides" at an amusement park. She was ecstatic! We also went to SplahCountry, which both of the kids thoroughly enjoyed. My sister and her family and my parents were also on the trip with us. We had a cabin for all of us that included an indoor pool, hot tub, game room, theater room, and a pool table. I have a nephew and 2 nieces, and all of the kids (including mine) shared a room with bunk beds. The kids had a blast. My son's favorite part was when we visited Goats on the Roof and he rode the Alpine Coaster. My daughter loved going to the Hatfield and McCoy Dinner Show. We sat in the Splash Zone and she even was called up on stage! She was very excited to be able to go up on stage. After the show we were able to purchase a copy of our show, so we will always have the memory of her being a part of it. I love being able to spend time with my family and see my children experience new things.
A: | recalled
****
|
Teacher:You are given a target race, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.
Teacher: Now, understand the problem? Solve this instance: Target: Ethiopian
An Ethiopian man was walking around college campus. He is an exchange student and barely speaks english.
Student: | stereotype |
Detailed Instructions: In this task you are expected to write an SQL query that will return the data asked for in the question. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the "SELECT" statement. Next, you use a "FROM" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the "AS" statement. You can reference that table by whatever name follows the "AS" statement. If you want to select data from multiple tables you need to use the "JOIN" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the "ON" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the "WHERE" statement to specify that only rows with column values statisfying a certain condition, should be returned. The "GROUP BY" statement will group rows together that have equal column values for whatever columns follows the statement. The "HAVING" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the "ORDER BY" command which will order the data by whatever aggregate function or column follows the statement. The "DESC" statement will sort in descending order and the "ASC" statement will sort in ascending order. Finally, you can use the "LIMIT" statement to return a certain number of rows. When "*" is used in an SQL statement every column is returned. For example, SELECT * FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.
Problem:Show the names of the three most recent festivals.
Solution: | SELECT Festival_Name FROM festival_detail ORDER BY YEAR DESC LIMIT 3 |
In this task, you are given a country name and you need to answer with the government type of the country, as of the year 2015. The following are possible government types that are considered valid answers: Republic, Parliamentary Coprincipality, Federal Republic, Monarchy, Islamic Republic, Constitutional Monarchy, Parlementary Monarchy, Federation.
One example: Angola
Solution is here: Republic
Explanation: Republic is the government type of the country called Angola.
Now, solve this: Saint Lucia
Solution: | Constitutional Monarchy |
Teacher: In this task, you are given a movie review in Persian, and you have to extract aspects of the movie mentioned in the text. We define aspects as music(موسیقی), directing(کارگردانی), screenplay/story(داستان), acting/performance(بازی), cinematography(فیلمبرداری), and scene(صحنه). Although there might be multiple aspects in a review, we only need you to write one aspect.
Teacher: Now, understand the problem? If you are still confused, see the following example:
فیلم متوسطی بود از لحاظ داستان ولی خوشحالم که سینمای ایران یک نیم نگاهی به این قشر از جامعه مون کرد.نا گفته نماندگفتگو های پر تامل و تاثیرگذاری داشت با این حال امیدوارم که تماشاچیان عزیز در دام "خطالی عاطفی" نیوفتاده باشند.
Solution: داستان
Reason: This is a good example. The review is about the story of the movie.
Now, solve this instance: داستان جالبی داشت ولی بازی ها می تونست قوی تر و پررنگ تر باشه
Student: | داستان |
In this task, you are given a hateful post in Bengali that expresses hate or encourages violence towards a person or a group based on the protected characteristics such as race, religion, sex, and sexual orientation. You are expected to classify the post into two classes: religious or non-political religious on the topic.
Let me give you an example: কোনো মেয়ে ইসলাম ধর্ম গ্রহণ করলে আমি তাকে বিয়ে করতে রাজি(আমি কুরআন হাফেজ)।
The answer to this example can be: religious
Here is why: Here it expresses hate against the religion, hence tagged as religious.
OK. solve this:
শ্রীকৃষ্ণ প্লে বয় ছিল টিক কইসস।কারন তদের আল্লার পুটকি দেখে বুঝা যায় আল্লার গুয়া ফাঠাইয়া প্লেবয় হইসে।
Answer: | religious |
Teacher: In this task, you are given a movie review in Persian, and you have to extract aspects of the movie mentioned in the text. We define aspects as music(موسیقی), directing(کارگردانی), screenplay/story(داستان), acting/performance(بازی), cinematography(فیلمبرداری), and scene(صحنه). Although there might be multiple aspects in a review, we only need you to write one aspect.
Teacher: Now, understand the problem? If you are still confused, see the following example:
فیلم متوسطی بود از لحاظ داستان ولی خوشحالم که سینمای ایران یک نیم نگاهی به این قشر از جامعه مون کرد.نا گفته نماندگفتگو های پر تامل و تاثیرگذاری داشت با این حال امیدوارم که تماشاچیان عزیز در دام "خطالی عاطفی" نیوفتاده باشند.
Solution: داستان
Reason: This is a good example. The review is about the story of the movie.
Now, solve this instance: واقعا فیلمی فوق العاده جذاب و دوست داشتنی بود.......موضوعی رمانتیک و عاشقانه و موسیقی های شاد و بی نظیر و گریم ها و صحنه ها و لباس های متفاوت و موقعیت های کمدی و طنز بی نظیر........حتما ببینید
Student: | موسیقی |
Teacher:Given an entity as input, output another entity which is part of the input entity. These are entities of meronym. In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., output entity) is in a part-of relationship with its holonym (i.e., input entity).
Teacher: Now, understand the problem? Solve this instance: chocolate cake
Student: | matter |
You are given first 5 messages from a series of message exchanges between 2 persons playing the game of Diplomacy which is an American strategic board game. You need to generate the next message. The message should be generated such that it fits the context seen so far. Avoid the text that is (i) tangent to the context, (ii) repeats the context.
Example Input: ["Hey neighbors ~~\nWhat would you say to a western triple? We'd have to be careful about it and simulate some in fighting to prevent the east from teaming up in response, but I think we can pull it off", "I'm willing to consider it if all 3 are in", 'France says their in, so I think we can make this work', 'What would you propose from here?', "I'd say we can take on Russia pretty well together -- I can go North to take Stp by 02 or 03 and you can bounce them out of Swe and I'd support you in in the coming years\nFrom there, Id try to march my armies south on the Eastern edge of the board, you could go through the middle towards Austria, and France can be swinging south through Italy in the meantime"]
Example Output: That seems fair enough, I'm in
Example Input: ["Hi France! I don't think we have a ton to talk about yet, but if you're planning to go in against Italy that's certainly something I'd like to know.", 'Thanks for reaching out. How do you generally feel about working with Italy?', 'If Italy wants it, it can be a powerful alliance, but in my experience Italy rarely wants it badly enough.', "That's true, and my experience as well. It's tricky since if he's not going after me or yoy, then what are his plans? If Italy isn't planning to Lepanto then it is worrying for one of us", "Well I haven't heard *too* much from Italy yet, but once I find out more about his current intentions I will certainly let you know."]
Example Output: Nice, things are looking up for you with the Russia/Turkey conflict and a seemingly friendly Italy.
Example Input: ['Hello down there, Sultan!\n\nAnything we need to talk about early, or should we just see what happens early?\n\nBest,\n\n- Kaiser', 'Eh, I have the luxury of a boring country that CAN chill out and see how things shake out. \nAnd as much as I personally enjoy opening to Tyrolia as Germany, other people tend to look at me weird if I suggest it, so...I guess all I can really five into is to ask that you give me a heads up if you decide to pick a fight with a mutual neighbor so I can pile on', "So, you were going for the Slingshot Juggernaut, and had the rug pulled out, huh? That hurts. And Austria is in no position to provide much help.\n\nWhat's the plan from this point?", "My hands are tied with my positioning and an NAP that runs through the end of this year, but I'm happy to work as an intermediary with you and Austria to help coordinate.\n\nI've given you one bit of help - Russia can't build in Warsaw, so it takes one unit out of the South.", "Ugh, what a pain in the ass. I can't even rotate on him in a meaningful time frame, and Austria's going to be no help any time soon beyond protecting Bulgaria this turn."]
Example Output: | You could take him down together, unless he's working with Italy. Even if he's not, Italy's going to feed on Austria - he's pretty committed - and come after you since you're exposed. The upside is just that they wouldn't likely be explicitly helping each other.
I don't have anything preventing me from going at Italy, and he's really wrecking everything right now. Plus, silent. As far as I know, towards everyone.
|
Teacher:In this task you will be given a list of integers. You should remove any integer that is not prime. A prime integer is an integer that is only divisible by '1' and itself. The output should be the list of prime numbers in the input list. If there are no primes in the input list an empty list ("[]") should be returned.
Teacher: Now, understand the problem? Solve this instance: [34, 181, 906, 623, 377, 903, 261, 779, 281, 86, 197, 376]
Student: | [181, 281, 197] |
In this task you will be given a list of numbers and you should remove all duplicates in the list. If every number is repeated in the list an empty list should be returned. Your list should be numbers inside brackets, just like the given list.
Q: [0, 0, 7, 0, 5]
A: | [7, 5] |
Generate a 5-star review (1 being lowest and 5 being highest) about an app with package de.danoeh.antennapod.
Ans: Great app So easy to use. So elegant. So helpful. No ads. No spyware. no fuss.
Generate a 4-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.
Ans: Aa Aa
Generate a 5-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.
Ans: Tried
Generate a 5-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.
| Ans: Great app. A must-have! Just download it already!! |
Detailed Instructions: In this task, you will be given sentences in which you have to recognize the name of the body cells. A cell is a mass of cytoplasm that is bound externally by a cell membrane. Usually microscopic in size, cells are the smallest structural units of living matter and compose all living things. Although there might be several correct answers, you need to write one of them.
Q: Neutrophils were stimulated in vitro by Escherichia coli , phorbol 12 - phorbol myristate 13 - acetate ( PMA ) , and peptide N - formyl - Met - Leu - Phe ( fMLP ) .
A: | Neutrophils |
Detailed Instructions: In this task, you're given two articles in the Thai language and the possible genre they belong to in the English language. Determine if the two articles share a positive sentiment on the given genre. Indicate your answer with Y for yes if they do and N for no if they don't. Genres available include: politics,human_rights,quality_of_life,international,social,environment,economics,culture,labor,national_security,ict,education
Problem:Article1:
Title: จับหนุ่มเสื้อแดงหลังร่วมงานศพอภิวันท์ ระบุมีภาพชุมนุมต้านรัฐประหาร
Body: เวลาประมาณ 22.30น. 19 ตุลาคม 2557 ประชาไทได้รับรายงานว่า เจ้าหน้าที่ทหารได้ทำการจับกุมชายเสื้อแดงที่วัดบางไผ่ หลังจากที่เข้าร่วมงาน พอ.ดร.อภินันท์ ทราบชื่อภายหลังว่า นายหนึ่ง เกตุสกุล อายุ 28ปี อยู่แขวง บางบัว เขต บางเขน กรุงเทพฯ โดยเบื้องต้นได้ถูกนำตัวมาสอบสวนที่ สน. พญาไท. ซึ่งคาดว่าจะเป็นพื้นที่เกิดเหตุ เจ้าหน้าที่ทหารได้อนุญาตให้ นส.ศศินันท์ ธรรมนิฐินันท์ ทนายความจากศูนย์ทนายความเพื่อสิทธิมนุษยชน ได้เข้าพบผู้ต้องหาและร่วมฟังการสอบสวนผู้ต้องหา
หลังเสร็จสิ้นการสอบสวน ศศินันท์ ธรรมนิฐินันท์ ทนายความจากศูนย์ทนายความเพื่อสิทธิมนุษยชน ได้กล่าวกับประชาไทว่า นายหนึ่งได้ถูกจับกุมขณะกำลังเดินทางกลับจากงานฌาปณกิจ พ.อ. ดร.อภินันท์ วิริยะชัย อดีต สส.พรรคเพื่อไทย และแกนนำคนเสื้อแดง เหตุเกิดในช่วงเวลาประมาณ 20.00 ขณะที่นายหนึ่งกำลังขึ้นท้ายรถกระบะเพื่อเดินทางกลับบ้านทหารนอกเครื่องแบบจำนวน 4 นาย ได้ดึงแขนนายหนึ่งลงจากรถพาไปคุยแล้วควบคุมตัวมาสอบสวนยัง สน.พญาไท
โดยเบื้องต้นทางทหารแจ้งว่า นายหนึ่งเป็นบุคคลที่ถูกบันทึกอยู่ในภาพเหตุการณ์ การชุมนุมต่อต้านรัฐประหาร ที่บริเวณอนุสาวรีย์ชัย เมื่อวันที่ 28 พฤษภาคม 2557 โดยในเหตุการณ์นั้นได้มีการทำลายรถทหาร
หลังการสอบสวนเบื้องต้นแล้วเสร็จ ทหารได้นำตัวนายหนึ่งออกจาก สน.พญาไทไปควบคุมตัวไว้โดยไม่ได้แจ้งสถานที่ควบคุมต่อญาติและทนายฯ แต่แจ้งว่าจะนำตัวมายัง สน.พญาไท เวลาประมาณ 09.00น. ของวันที่20 เพื่อทำเรื่องส่งตัวตัวไปขอฝากขังยังศาลทหาร กระทรวงกลาโหม
Article 2:
Title: ม็อบเรียกร้อง "เจิมศักดิ์-ประทิน-นิรันดร์" ลาออก
Body: ณ บริเวณตรงข้ามรัฐสภา ด้านกำแพงสวนสัตว์ดุสิต มีประชาชนประมาณ 30 คน อ้างตัวว่าเป็น "แนวร่วมสมานฉันท์แห่งชาติ" ได้ปราศรัยโจมตีนพ. นิรันดร์ พิทักษ์วัชระ, นายเจิมศักดิ์ ปิ่นทอง และพล. ต. อ. ประทิน สันติประภพ รวมทั้งนักวิชาการที่ร่วมลงรายชื่อเรียกร้องให้นายกรัฐมนตรีขอโทษประชาชน อีกทั้งยังมีการติดป้ายผ้าแสดงข้อความโจมตี โดยมีผู้ให้ความสนใจประปราย
กลุ่มผู้ชุมนุมยังได้แจกเอกสารโจมตี โดยระบุว่าบุคคลเหล่านี้มีส่วนในการสร้างสถานการณ์ให้รุนแรงขึ้นโดยหวังผลประโยชน์ทางการเมือง อีกทั้งยังระบุว่าบุคคลเหล่านี้ไม่เคยออกมาเรียกร้องให้ผู้บริสุทธิ์ที่เสียชีวิตเลย
นอกจากกลุ่มนี้ ยังมีกลุ่มประชาชนที่เรียกตัวเองว่า "กลุ่มสามัคคีไทยรักชาติ" เข้ายื่นจดหมายต่อนายสุชน ชาลีเครือ ประธานวุฒิสภา เรียกร้องให้นายเจิมศักดิ์ และพล. ต. อ. ประทินลาออก โดยระบุเหตุผลว่านายเจิมศักดิ์ใช้หน้าที่ สว. ในการต่อต้านรัฐบาลในทุกเรื่องอย่างไม่ถูกกาลเทศะ โดยเฉพาะในการออกเอกสาร "ความจริงที่ตากใบ" โดยไม่เสนอข้อเท็จจริงของทุกฝ่ายในเหตุการณ์ ส่วนพล. ต. อ. ประทินนั้นมีพฤติกรรมไม่เหมาะสมในการใช้อารมณ์กับคนที่ไม่เห็นด้วยกับตนเอง โดยเฉพาะอย่างยิ่งการออกมาปกป้องนายเจิมศักดิ์ในการชี้แจงเอกสาร "ความจริงที่ตากใบ" จนทำให้เกิดเหตุชกต่อยกับสว. ด้วยกันเอง
ภาณุวัฒน์ อภิวัฒนชัย
ประชาไทรายงาน
Do both the articles share the same sentiment for the genre: environment?
Solution: | no |
Given a part of privacy policy text, identify the purpose for which the user information is collected/used. The purpose should be given inside the policy text, answer as 'Not Specified' otherwise
When a minor change is made to the privacy policy that does not significantly affect data practices, the policy date is updated or information about the change is posted as part of the policy. Users' choices regarding policy changes are not mentioned or are unclear. | Not Specified |
You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.
I have a frog on my head | one day i find a frog on my head and i say why be you on my head he jump on my bed my name be fred he say so i say the end |
Teacher:In this task you are given a list of numbers and you need to find the average of each two consecutive values. The average of two numbers a and b is calculated as: (a + b) /2. The output should be a list of the averages of each two consecutive values. A list is presented with two brackets and comma-separated values, like: [1,2,3].
Teacher: Now, understand the problem? Solve this instance: [-5, -22, 93, 68, 29, 62, -33, 71, 45, -58, -73, -14]
Student: | [-13.5, 35.5, 80.5, 48.5, 45.5, 14.5, 19.0, 58.0, -6.5, -65.5, -43.5] |
In this task, you are given inputs 'i', 'j', and A, where 'i' and 'j' are integers and A is a list. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. 'i' and 'j' will be non-negative, and will always have a value less than the length of A. 'i' will always be less than 'j'. Perform the operations in order, i.e., do not reverse first and then concatenate.
Let me give you an example: 1, 3, ['238', 'h', '92', 'U', '2799']
The answer to this example can be: 29h832
Here is why: Here, concatenating all the elements between the 1st element and 3rd element and then reversing the string gives '29h832'.
OK. solve this:
3, 17, ['6425', '7643', 'e', 'n', '2507', 'T', 'h', 'n', '671', '9599', '6061', 'E', 'L', '6385', 'S', 'x', '3943', '3539', 'b', 'x', 'n']
Answer: | 3493xS5836LE16069959176nhT7052ne |
In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.
--------
Question: [[25, 34], [43, 2, 40, -25, -45], [16, -49, 40, 18]]
Answer: [34, 80, 11520]
Question: [[15, -22, 42], [-39, -34, 1, -19, -45], [19, 13, 16], [-21, -20], [14, -29, -11, -5, -4]]
Answer: [-924, -34, 16, -20, -56]
Question: [[30, 35, -5, -22, -35], [29, -8], [-37, -19, 4, -31]]
Answer: | [-660, -8, 4]
|
Definition: The task is to identify if a given passage or sentence has proper punctuation. This includes proper capitalization and the use of punctuations such as commas, semi-colons and full-stops. The answer is True if all punctuation is properly applied, else the answer is False.
Input: Under the reckless contempt for regulations,
Output: | False |
Convert a disfluent question to a proper question. A disfluent question is a question that has some interruptions in it while framing. A proper question is the correct form of the question without any disfluency.
Q: What are buckles facing downwards in a fault called no no let's say that the tops of the rock units within the folds remain pointing upwards, what are they called?
A: If the tops of the rock units within the folds remain pointing upwards, they are called what?
****
Q: Is the connection sorry the packet header long?
A: Is the packet header long
****
Q: Who has the no no I mean what happens if a member doesn't vote the party line?
A: | What happens if a member doesn't vote the party line?
****
|
Detailed Instructions: In this task, you are given a string with unique characters in it and you need to return the character from the string which has the maximum ASCII value. ASCII stands for American Standard Code For Information Interchange and It assigns a unique number to each character. The characters [a - z] have an ASCII range of 97-122 and [A-Z] have an ASCII range of 65-90 respectively.
Problem:dDFOr
Solution: | r |
In this task, you are given a sentence in the Bulgarian language. Your task is to convert it to Greek language.
Example Input: ABILIFY е показан за лечение на умерени до тежки манийни епизоди при биполярно афективно разстройство и за предотвратяване на нови манийни епизоди при пациенти, които страдат предимно от манийни епизоди, и чиито манийни епизоди се повлияват от лечение с арипипразол (вж. точка 5. 1)
Example Output: Το ABILIFY ενδείκνυται για τη θεραπεία ήπιων έως σοβαρών μανιακών επεισοδίων σε Διπολική Διαταραχή τύπου Ι και για την πρόληψη νέου μανιακού επεισοδίου σε ασθενείς που εμφάνισαν κυρίως μανιακά επεισόδια και των οποίων τα μανιακά επεισόδια ανταποκρίθηκαν στη θεραπεία με αριπιπραζόλη (βλέπε παράγραφο 5. 1).
Example Input: Абсолютната перорална бионаличност при таблетната форма е 87%.
Example Output: Η απόλυτη βιοδιαθεσιμότητα μετά από τη λήψη δισκίων από το στόμα είναι 87%.
Example Input: Ето защо, при пушачи не се налага промяна на дозата.
Example Output: | Επομένως, δεν απαιτείται προσαρμογή της δόσης για τους καπνιστές.
|
Given the task definition and input, reply with output. You are given a question-answer pair. Answer with their type. Pay attention that there may be more than one correct type, but you only have to choose one. In your responses, use of the following types:
(1) Humans: Any individual or group of humans, including fictional ones (e.g., a group or organization of persons , an individual, title of a person, description of a person);
(2) Event: Any phenomenon natural or artificial (e.g., named hurricanes, Battles, Wars, Sports events, Terrorist attacks);
(3) Entity: A thing with distinct and independent existence (Animals, Organs of body, Colors, Inventions, books and other creative pieces, Currency name, Diseases, and medicine, Food, Musical instrument, Languages, Plants, Products, Religions, Sports, Elements and substances, Symbols and signs, Techniques and methods, Equivalent terms, Vehicles);
(4) Facility: Something built for a particular purpose (Buildings, Airports, Highways, Bridges);
(5) Location: A place (Cities, Countries, Mountains, States);
(6) Law: Named documents made into laws (e.g., “the first amendment”, "civil rights act");
(7) Organization: an organized body of people with a particular purpose (Company names, e.g. Google, Cults or terrorist groups, e.g. Al Qaeda);
(8) Date: Absolute or relative dates or periods, bigger than 1 day (Years, Range, e.g. from Monday to Tuesday, or during the 20th century, Approximate time);
(9) Time: Any temporal range/unit that is shorter than a day (e.g., 2 o'clock, 1 pm);
(10) Money: Monetary values, including unit (e.g., "$26", "914$");
(11) Quantity: postcodes or other codes, the number of sth, Ranks, fractions, speed, temperature, size, area, and volume, weight (e.g., "26 degree" "17 inch");
(12) Description: description and abstract concepts (e.g., the definition of something, the manner of an action, reasons);
(13) Abbreviation: expression abbreviated (e.g., AMT = abbreviation of Amazon Mechanical Turk). Don't generate any word that is not mentioned in the list of types (Humans, Event, Entity, Facility, Location, Law, Organization, Date, Time, Money, Quantity, Description, Abbreviation). If you can not associate any of the given types with the provided question and answer pair, respond "Other".
Question: Who does Beyoncé describe as the definition of inspiration? (Answer: Oprah Winfrey).
| Entity. |
Given the following Catalan sentence, indicate the name entities (i.e., the real-world objects such as a person, location, organization, etc. that can be denoted with a proper name) such as 'New York Times'. For each words of a named-entity, indicate their type 'LOC' or 'ORG' or 'PER', where 'LOC' indicates a location entity (such as 'New York City', 'ORG' indicates the token of an organization (such as 'Amazon'), 'PER' indicates the tokens of a person entity (such as 'Jeff Bezos'). Named entities with other types should be indicated with 'MISC'. To indicate boundaries of an entity, use IOB (Inside-Output-Begin) prefixes. The B- prefix before a tag indicates that the word is the beginning of a named entity. The I- prefix indicates that the word is inside a bigger chunk. For example, you can break 'New York' to 'New' and 'York.' and tag them as 'B-LOC' and 'I-LOC'. Any token that doesn't belong to a named entity must be tagged with 'O'.
Ex Input:
Els funcionaris s' encarregaven del control de la higiene de les empreses càrniques de La Garrotxa , i per aquest motiu feien visites periòdiques i analítiques .
Ex Output:
Els (O) funcionaris (O) s' (O) encarregaven (O) del (O) control (O) de (O) la (O) higiene (O) de (O) les (O) empreses (O) càrniques (O) de (O) La (B-LOC) Garrotxa (I-LOC) , (O) i (O) per (O) aquest (O) motiu (O) feien (O) visites (O) periòdiques (O) i (O) analítiques (O) . (O)
Ex Input:
En aquest sentit han anunciat que han demanat una entrevista amb el conseller d' Indústria , Antoni Subirà , per a tractar aquest tema .
Ex Output:
En (O) aquest (O) sentit (O) han (O) anunciat (O) que (O) han (O) demanat (O) una (O) entrevista (O) amb (O) el (O) conseller (O) d' (O) Indústria (B-ORG) , (O) Antoni (B-PER) Subirà (I-PER) , (O) per (O) a (O) tractar (O) aquest (O) tema (O) . (O)
Ex Input:
El Tribunal Suprem ( TS ) ha confirmat la condemna a quatre anys d' inhabilitació especial i una multa de 3,6 milions de pessetes per a quatre veterinaris gironins , per haver -se beneficiat dels càrrecs públics que desenvolupaven i la seva relació amb les empreses càrniques de la zona en oferir -los serveis particulars .
Ex Output:
| El (O) Tribunal (B-ORG) Suprem (I-ORG) ( (O) TS (B-ORG) ) (O) ha (O) confirmat (O) la (O) condemna (O) a (O) quatre (O) anys (O) d' (O) inhabilitació (O) especial (O) i (O) una (O) multa (O) de (O) 3,6 (O) milions (O) de (O) pessetes (O) per (O) a (O) quatre (O) veterinaris (O) gironins (O) , (O) per (O) haver (O) -se (O) beneficiat (O) dels (O) càrrecs (O) públics (O) que (O) desenvolupaven (O) i (O) la (O) seva (O) relació (O) amb (O) les (O) empreses (O) càrniques (O) de (O) la (O) zona (O) en (O) oferir (O) -los (O) serveis (O) particulars (O) . (O)
|
Adverse drug reactions are appreciably harmful or unpleasant reactions resulting from an intervention related to the use of medical products, which predicts hazard from future administration and warrants prevention or specific treatment, or alteration of the dosage regimen, or withdrawal of the product. Given medical case reports extracted from MEDLINE, the task is to classify whether the case report mentions the presence of any adverse drug reaction. Classify your answers into non-adverse drug event and adverse drug event.
Laboratory investigations confirmed a metabolic acidosis (pH 7.15) and hyperchloremia.
non-adverse drug event
When the patient discontinued taking the drugs by herself because of subsiding of these symptoms, severe panic anxiety appeared.
non-adverse drug event
Imidazoline intoxication in children.
| adverse drug event
|
In this task you are given a Chinese paragraph related to a criminal case, your job is to give an answer of what the criminal charge is. Take note a) if there are multiple charges only one needs to be outputted b) the criminal charge should be in Chinese.
赤水市人民检察院起诉指控：2013年12月6日14时许，赤水市丙安乡人民政府组织工作人员对被告人袁某某违法修建的房屋第五层建筑进行了强行拆除，被告人袁某某心生不满，认为是赤水市丙安乡人民政府工作人员黄某出尔反尔，欺骗了自己。被告人袁某某得知黄某在赤水市丙安派出所后，便从地上检了一根錾子到赤水市丙安派出所找黄某，当其来到赤水市丙安派出所时，遇见赤水市丙安乡派出所的贵C＊＊＊＊警车外出，便故意站在车行道上不让警车行驶。开车民警下车询问时，被告人袁某某用手中錾子敲打贵C＊＊＊＊警车的引擎盖，然后又用錾子将贵C＊＊＊＊警车的前后挡风玻璃、玻璃窗、警灯以及警车的大小灯打坏，导致该警车无法正常使用。案发后，经赤水市价格认证中心鉴定，被告人袁某某毁坏的贵C＊＊＊＊警车修复费用为人民币8415.00元。除以上指控事实外，另查明：被告人袁某某系肢体残疾肆级。案发后，赔偿了赤水市丙安派出所经济损失5000.00元。2014年1月2日，赤水市丙安派出所出具谅解书，鉴于被告人袁某某有悔罪表现，家庭困难，赔偿了经济损失，对其行为谅解，要求对其从宽处罚。 | 故意毁坏财物 |
You will be given a definition of a task first, then some input of the task.
In this task you will be given a list of integers. You should remove any integer that is not prime. A prime integer is an integer that is only divisible by '1' and itself. The output should be the list of prime numbers in the input list. If there are no primes in the input list an empty list ("[]") should be returned.
[909, 542]
Output: | [] |
Given the sentence, generate "yes, and" response. "Yes, and" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated ("Yes") and then expand on that line of thought or context ("and..."). 1 In short, a "Yes, and" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a "Yes, and" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'.
Hi, hope you don't mind, I was eavesdropping and I heard you say the word toilet several times. | I do that when something's on my mind. I have no filter. |
Detailed Instructions: In this task, you are given a string with unique characters in it and you need to return the character from the string which has the maximum ASCII value. ASCII stands for American Standard Code For Information Interchange and It assigns a unique number to each character. The characters [a - z] have an ASCII range of 97-122 and [A-Z] have an ASCII range of 65-90 respectively.
Problem:wLAdynqoBNa
Solution: | y |
Adverse drug reactions are appreciably harmful or unpleasant reactions resulting from an intervention related to the use of medical products, which predicts hazard from future administration and warrants prevention or specific treatment, or alteration of the dosage regimen, or withdrawal of the product. Given medical case reports extracted from MEDLINE, the task is to classify whether the case report mentions the presence of any adverse drug reaction. Classify your answers into non-adverse drug event and adverse drug event.
CONCLUSIONS: Topical imiquimod 5% cream seems to be a useful treatment for eyelid nodular basal cell carcinoma in selected cases, but further long-term studies are needed to assess the efficacy and safety of this approach.
non-adverse drug event
CASE DESCRIPTION: A 24-year-old 732-kg (1,610-lb) pregnant Belgian draft horse mare developed neuropathy and signs of intractable pain following colic surgery.
non-adverse drug event
Exacerbation of schizophrenia associated with amantadine.
| adverse drug event
|
In this task, you are given two sets, and a question. You need to find whether an element is at the intersection of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. The intersection of two given sets is the largest set which contains all the elements that are common to both sets. An element is at the intersection of two given sets, A and B, if common to both A and B. Classify your answers into 'Yes' or 'No'.
Set1: '{1, 2, 9, 12, 13, 14, 16, 19, 20}', Set2: '{3, 4, 5, 6, 7, 12, 13, 14, 16, 18}'. Is the element '19' in the intersection of Set1 and Set2 ? | No |
instruction:
In this task, you will be presented with a question having multiple possible answers in Swahili language. And you should choose a most suitable option out of "A", "B", "C", "D", and "E" based on your commonsense knowledge.
question:
Question: Ikiwa ungekuwa mvivu labda ungechagua kutazama runinga kwa sababu tu?
Options: A kuburudishwa B umechoka C Chomeka D kupata starehe E tazama onyesho linalopendwa
answer:
B
question:
Question: Kutakuwa na zaidi ya watu laki moja kwenye uwanja wa mpira wikendi hiyo, ilikuwa mahali maarufu zaidi kwa nini?
Options: A sekondari B wachezaji C chuo kikuu D texas E oklahoma
answer:
C
question:
Question: Je! Ungekuwa unajenga nini ukibuni mahali pa mkosoaji anayekasirika kukaa?
Options: A kueneza magonjwa B kinamasi C kambi za wadudu D condo ya paka E kuruka mbali
answer:
| C
|
Given the task definition, example input & output, solve the new input case.
In this task, you are given a country name and you need to return the calling code of the given country. Your output must be formatted as a plus sign (+), followed by the calling code number
Example: Abkhazia
Output: +99544
+99544 is the calling code of the country called Abkhazia.
New input case for you: Slovenia
Output: | +386 |
instruction:
Given a pair of words, generate the relation between them. The first word is called the 'concept' and the second word is called the 'relatum' The relation must be one of the following: co-hyponym (coordinate), hypernym, meronym, attribute, event, or random. A coordinate relation indicates that the concept and relatum belong to the same semantic class. A hypernym relation indicates that the relatum is a category of which the concept is a specific instance. A meronym relation implies that relatum is a part/component/organ/member of the concept. An attribute relation is when the relatum is an adjective expressing an attribute of the concept. An event relation holds when the relatum is a verb referring to an action/activity/happening/event that is performed by or with the concept. If the relatum and concept are unrelated, the relation between them is 'random'. Classify your answers into coord, hyper, mero, attri, event, and random.
question:
Concept: tiger, Relatum: carnivore.
answer:
hyper
question:
Concept: lion, Relatum: chordate.
answer:
hyper
question:
Concept: bag, Relatum: handle.
answer:
| mero
|
Teacher:Your task is to localize given English phrase into Telugu language. When localising, follow these rules - (1) General names and concepts can be translated (2) Domain specific names can just be transliterated (3) Localised phrases can have both partial translated and transliterated parts (4) But only partial translation or only partial transliteration is not allowed (5) Copy special characters and numbers as is
Teacher: Now, understand the problem? Solve this instance: Native Plasma widget written in Ruby
Student: | జావాస్క్రిప్ట్లో వ్రాసిన నేటివ్ ప్లాజ్మా విడ్జ్ట్ |
In this task, you are given a movie review in Persian, and you have to extract aspects of the movie mentioned in the text. We define aspects as music(موسیقی), directing(کارگردانی), screenplay/story(داستان), acting/performance(بازی), cinematography(فیلمبرداری), and scene(صحنه). Although there might be multiple aspects in a review, we only need you to write one aspect.
--------
Question: واقعیت تلخ ،طنز هم داشت من دوسش داشتم و از تماشای این فیلم لذت بردم مهم اینه که تهش مشخص بود و مشخص شد نیاز نبود بری توی کما برای یافتن نتیجه و بازی پسر بچه و نگاه های عاشقانه ش معرکه بود چون بر مبنای عشق و علاقه بود دوسش داشتم و روند فیلم آروم بود
Answer: داستان
Question: یه فیلم خوب، تمیز و شریف نگاه جدیدی که کارگردان به مرگ تختی کرده بود ورای خودکشی در اثر فشارهای زندگی و زن و ... و یا قتل به دست حکومت بود. تختی به جایی رسید که دیگه این دنیا با همه زرق و برقش رو دوست نداشت. تختی این دنیایی نبود.
Answer: کارگردانی
Question: فیلم ، فیلمنامه ندارد و از به هم چسبیدن چند کلیپ تشکیل شده است که می تواند سرگرم کننده باشد ولی مسئله ای که مرا متعجب می کند آن است که چرا فیلمی که ژانر کمدی دارد در آخر این قدر تغییر جهت می دهد
Answer: | داستان
|
In this task you need to give reasons to justify the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a question about how to justify the coreference between a noun phrase and the target pronoun. Good practices involve the discussion about how the descriptions attached to the targeted pronoun relate to the noun phrase candidate in the question. The reasoning could come from one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. Write the sentence in natural language.
[EX Q]: Sentence: I used an old rag to clean the knife, and then I put it in the trash.
Question: Why does the 'it' refer to the rag?
[EX A]: Because The rag was already old, so it makes sense to throw it away.
[EX Q]: Sentence: The sun was covered by a thick cloud all morning, but luckily, by the time the picnic started, it was out.
Question: Why does the 'it' refer to the sun?
[EX A]: Because the sun is the thing being covered, so "it" is out when it is no longer covered. The cloud can't cover itself.
[EX Q]: Sentence: The sack of potatoes had been placed above the bag of flour, so it had to be moved first.
Question: Why does the 'it' refer to the sack of potatoes?
[EX A]: | Because Its on top.
|
Detailed Instructions: Given a prompt and two completions from a language model, select the completion that is the least toxic with respect to continuing the prompt. Toxicity is defined as a rude, disrespectful, or unreasonable statement that is likely to make you leave a discussion. Generate either Completion A or Completion B.
Problem:Prompt: typo. That should have said GZ told investigators that was
Completion A: the truth. It shouldn't have. They had no proof. Why was he fired? Because he got the truth, not because
Completion B: how he knew he didn't commit murder but rather that he was the target of his abuse. This isn't enough. For years,
Solution: | Completion A |
You will be given a definition of a task first, then some input of the task.
In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.
['N', '2', '5']
Output: | [['N', '2'], ['N', '5'], ['2', '5']] |
Definition: In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about "doctors", you can talk about "health" or "diagnosis", but don't mention "aliens". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: "She likes cakes." is changed to "She doesn't like cakes."
Input: Beginning: A pilot flew his plane in a nearly cloudless sky. Middle: Suddenly, he flew into a major storm system and it became cloudy and grey. Ending: The pilot emerged on the other side and kept flying.
Output: | Suddenly, he flew into a major mountain and it became inescapable. |
Detailed Instructions: Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.
Q: 03:25:53 PM occured before 5:08:28 PM but after 12:55:24 AM
A: | False |
Detailed Instructions: In this task, you are given a country name, and you need to return the year in which the country became independent. Independence is a nation's independence or statehood, usually after ceasing to be a group or part of another nation or state, or more rarely after the end of military occupation.
Problem:Spain
Solution: | 1492 |
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.
Problem:Was this president born on the east coast? What college degree(s) did this president have?
Solution: | Did this president go to college in the state he was born in? |
Given the task definition and input, reply with output. In this task, you have to generate the named entities (NER) given its ingredients of the recipe. Named entities are the names of the items without their quantity.
Puff pastry (philo), salamon creme cheese
| pastry, creme cheese |
Detailed Instructions: Indicate all the pronouns (they, them, you, he, his, her, you, it, etc.) present in the given sentence. If there are multiple such pronouns in a sentence, then list them in the order of their first appearance in the given sentence. If a pronoun appears multiple times in a sentence, list it only once.
See one example below:
Problem: the user changed his password from grwqwu8jyc to willow-towered canopy huntertropic wrestles as it was easy to remember.
Solution: his, it
Explanation: In this statement, 'it' is the pronoun used for password, and 'his' is used for the user.
Problem: i took the water bottle out of the backpack so that it would be handy.
Solution: | i, it |
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 an english sentence and a kurdish sentence you have to determine if they both are faithful translations of each other.
Construct an answer that is 'Yes' if the second 'Kurdish' sentence is a translation of 'English' sentence and 'No' otherwise
'English : Diyarbakır 2nd Criminal Court of Peace has issued a gag order on the bomb attack on police shuttle in Diyarbakır.', 'Kurdish : Biryara qedexekirinê di rûpela Lijneya Bilnd a Radyo û Televizyonan (RTUK) de bi daxuyaniyek hat diyarkirin û wiha hat gotin:'
Solution: Yes
Why? The answer is 'Yes' because the second sentence is a consise and faithful translation of 'English' sentence into 'Kurdish'
New input: 'English : — garo paylan (@GaroPaylan) 18 Mayıs 2016','Kurdish : — garo paylan (@GaroPaylan) 18 Mayıs 2016'
Solution: | Yes |
Definition: In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command:
1. count: returns the number of rows in the view.
2. only: returns whether there is exactly one row in the view.
3. hop: returns the value under the header column of the row.
4. and: returns the boolean operation result of two arguments.
5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column.
6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column.
7. argmax/argmin: returns the row with the max/min value in header column.
8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column.
9. eq/not_eq: returns if the two arguments are equal.
10. round_eq: returns if the two arguments are roughly equal under certain tolerance.
11. greater/less: returns if the first argument is greater/less than the second argument.
12. diff: returns the difference between two arguments.
13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument.
14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument.
15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument.
16. filter_all: returns the view itself for the case of describing the whole table
17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument.
18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument.
19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument.
20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument.
21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument.
22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.
Input: the sum of the prize ( k ) record of all rows is 1920 .
Output: | round_eq { sum { all_rows ; prize ( k ) } ; 1920 } |
In this task you will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places.
--------
Question: [17.002, 179.236, 60.396, 98.09]
Answer: 88.681
Question: [117.913, 21.456, 98.401, -32.801, -20.798, 182.745, 201.277]
Answer: 81.17
Question: [163.905, 170.242, 94.071, 50.277, 218.562, -99.48, 180.404, -95.86, -43.816]
Answer: | 70.923
|
You will be given a definition of a task first, then some input of the task.
In this task, you will be given sentences in which your task is to recognize the name of the drug or medicine. Drugs are substances that change a person's mental or physical state. They can affect how your brain works, how you feel and behave, your understanding, and your senses. Although there might be several correct answers, you need to write one of them.
This is the first report of UFT-induced scleroderma-like reaction.
Output: | UFT |
TASK DEFINITION: In this task, you will be given a set of steps that are required to answer a specific question. Your job is to generate that question. Each given step refers to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.) Knowing those operations and how they appear in the input may help you generate more accurate questions.
Select: A select step is used to return a set of objects. There are no references to previous steps in a select step. template: Return [attributes]
Filter: A filter step is used to return results from a previous step to which a certain condition applies. template: Return [#step] [condition]
Project: A project step should return certain attributes of the results of a previous step. template: Return [attributes] of [#step]
Aggregate: An aggregate step returns an aggregator function applied on a step's result. template: Return the [aggregator] of [#step].
Group: A group step is an aggregator applied on attributes. template: Return the [aggregator] of [#step] for each [attribute]
Superlative: A superlative step is used to return the result with a highest/lowest attribute among other results. template: Return [#step1] [where] [#step2] [is] [highest / lowest]
Comparative: A comparative step is used when we need to compare an attribute with a number to filter results. template: Return [#step1] [where] [#step2] [comparator] [number]
Union: A union step is used to return results of two steps together. template: Return [#step1] [or / ,] [#step2]
Intersection: An intersection step returns the result that two steps have in common. template: Return [attribute] of both [#step1] and [#step2]
Discard: A discard step returns result of a step and excludes result of another step from it. template: Return [#step1] besides [#step2]
Sort: A sort returns result of another step in a specific order. template: Return [#step1] [ordered / sorted by] [#step2]
Is true: An is true step checks a condition on another result and returns a true or false. template: Return [is / if] [condition]
Arithmetic: An arithmatic step operates an arithmatic operation on one or more steps. template: Return the [arithmetic op.] of [#step1] [and] [#step2].
PROBLEM: #1 return items
#2 return shapes of #1
SOLUTION: what is the shape of these items?
PROBLEM: #1 return elvis
#2 return albums of #1
#3 return first of #2
#4 return year of #3
SOLUTION: what year did elvis release his first album?
PROBLEM: #1 return images
#2 return dogs in #1
#3 return mouth of #2
#4 return #2 where #3 is open
#5 return tongue of #4
#6 return #4 where #5 is visible
#7 return number of #6
#8 return if #7 is at least one
SOLUTION: | If at least one dog in an image in the pair has its mouth open and tongue visible.
|
Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.
--------
Question: I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT
Answer: look around left twice and turn around left twice
Question: I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT
Answer: look around left thrice and turn opposite right twice
Question: I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN
Answer: | run right twice after jump around right thrice
|
Part 1. Definition
In this task, you have given an input which is agent's reply, based on that you have to identify what will be users' command for that reply. The user generally asks a question related to event scheduling or information of the scheduled events. Agent reply based on the available information or do the task as per user command.
Part 2. Example
I didn't find any events with Gavin this week
Answer: Search for any meetings with Gavin for this week.
Explanation: The agent has replied about the events with Gavin, and the user has also asked about the same thing.
Part 3. Exercise
I've changed "Fingerlickin Food Sess" to be without Kim Possible, without Abby Gonano, and Katie Gonzales.
Answer: | That looks good to me. |
In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input.
--------
Question: name[Midsummer House], food[Italian], priceRange[less than £20], customer rating[low], near[All Bar One]
Answer: Midsummer House is a low cost restaurant serving pastas and wines located a short distance from All Bar One.
Question: name[The Rice Boat], food[Italian], priceRange[less than £20], customer rating[low], area[city centre], familyFriendly[no], near[Express by Holiday Inn]
Answer: The Italian restaurant, The Rice Boat, has a low customer rating and is not family-friendly, but meals are less than £20. It is located in the city centre near Express by Holiday Inn.
Question: name[The Phoenix], food[Italian], customer rating[low], area[riverside]
Answer: | The Phoenix is a low-customer-rated Italian restaurant on the riverside
|
Detailed Instructions: Turn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word "what" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, "A radio converts electricity into?"
Problem:Fact: The testicles connect to the vas deferens, then the seminal vesicles, then the prostate, then the urethra.
Solution: | What is the connection to the testicles that is between the vas deferens and the urethra? |
TASK DEFINITION: Two analogies that signify affordances are given in the form "A : B. C : ?". Affordance is the possibility of an action being done on an object, for example book is an affordance of writing. The phrase "A : B" implies that B is an affordance of A. Your task is to replace the question mark (?) with the appropriate affordance of the given action C, following the "A : B" relation. Your answer should be a single object without further explanation.
PROBLEM: swallow : pill. give : ?
SOLUTION: gift
PROBLEM: reload : gun. elect : ?
SOLUTION: president
PROBLEM: elect : congressman. send : ?
SOLUTION: | message
|
Detailed Instructions: In this task you are given a tweet. You must judge whether the tweet is ironic or not. We define two type of irony for this task ("polarity","situational"). Situational irony happens when a situation fails to meet some expectations. polarity irony happens when irony is achieved by inverting the intended sentence. Label the instances as "ironic" or "not" based on your judgment. Note that URLs in the text have been replaced with [Link].
Problem:When you have Challah French Toast on Christmas
Solution: | ironic |
TASK DEFINITION: The input is a conversation between an automated system and a user looking for suggestions for pubs, restaurants and coffee shops in Cambridge. In the dialogue, the user may provide some criteria for the type of place they want such as price range, cuisine, etc. Given such a dialogue, output the price range the user if looking for which can take one of four values: Cheap, Moderate, Expensive and Don't Care. Output cannot be any other value than the four values. Note that if the user asks for the prices of items provided at a pub, restaurant or coffee shop but doesn't mention the price range they are looking for then the correct classification will be Don't Care. If the user does not mention a particular price, the correct classification will be Don't Care.
PROBLEM: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'
User: 'sil'
System: 'What kind of venue are you looking for? For example, a cafe, or a restaurant.'
User: 'sil'
System: 'What kind of venue are you looking for? For example, a cafe, or a restaurant.'
User: 'i am looking for an expensive thai'
System: 'Let me confirm. You are looking for a restaurant.'
User: 'a thai restaurant'
System: 'The Wrestlers, which serves thai food, is an outstanding restaurant. It's in the expensive price range.'
User: 'yes'
System: 'The Wrestlers, which serves thai food, is an outstanding restaurant. It's in the expensive price range.'
User: 'what is the address post'
System: 'The Wrestlers is located on 337 Newmarket Road.'
User: 'what is the address and postcode'
System: 'The Wrestlers, which is in the area with the postcode CB5 8JE, is located on 337 Newmarket Road.'
User: 'what is the postcode'
System: 'The Wrestlers is in the area with the postcode CB5 8JE.'
User: 'what is the phone number'
System: 'The phone number of The Wrestlers is 01223566554.'
User: 'what is the phone number'
System: 'The phone number of The Wrestlers is 01223566554.'
User: 'thank you goodbye'
SOLUTION: Expensive
PROBLEM: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'
User: 'i am looking for a greek restaurant'
System: 'Are you looking for somewhere near a particular venue? For example, Byard Art, Kettle's Yard, or the Michaelhouse Centre.'
User: 'no'
System: 'The Eraina Taverna, which serves greek food, is an outstanding restaurant.'
User: 'whats the address phone number and the price'
System: 'The Eraina Taverna is located on 2 Free School Lane and its phone number is 01223902126. The price for main courses ranges from 6 pounds 50 to 13 pounds 95.'
User: 'thank you good bye'
SOLUTION: Don't Care
PROBLEM: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'
User: 'im looking for a moderately priced pub'
System: 'The Alma is a great pub and it's in the moderate price range.'
User: 'does it have a tv'
System: 'The Alma has a television.'
User: 'i need the address'
System: 'The Alma is on Russell Court.'
User: 'thank you good bye'
SOLUTION: | Moderate
|
Teacher:In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively.
Teacher: Now, understand the problem? Solve this instance: Premise: The teddy bear is tan with a brown nose and a white muzzle.
Hypothesis: The teddy bear has a black button for his nose.
Update: It's nose is cute and pink.
Student: | weakener |
Q: In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.
[528, 396, 857, 693]
A: | [530, 400, 860, 690] |
In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.
Input: Consider Input: ['4367', 'n', '9205', '6483', 'O', 'C', 'B', '521', '8481', '5713', '889', '8571', '9405', 'U', 'M', 'O', 'H', '463', '6445', '6913', 'R', 'Y', '6699', '5621', 'u', 'Y', '8687', '6237', 'Y', '1935', '4191', 'Y', 'H', '4629']
Output: 2, 5, 6, 7, 14, 15, 16, 17, 21, 22, 25, 26, 29, 32, 33
Input: Consider Input: ['i', 'h', '357', '7919', 'c', '2303', 'A', '537', 'z', 'A', 'J', '7021', 'J', 'e', '8761', '9071', '7859', 'Q', '677', '1121', 's', '3735', '1091', '5191', 'c', '8759']
Output: 1, 2, 5, 7, 9, 10, 11, 13, 14, 18, 21, 25
Input: Consider Input: ['t', '3547', '3279', '1947', 'a', '1571', '6385', '7349', '2787', 'h', '8699', 'p', '4325', '5275']
| Output: 1, 5, 10, 12
|
Detailed Instructions: In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.
Q: ['2', 'a', '1', 'Z', 'v']
A: | [['2', 'a', '1', 'Z'], ['2', 'a', '1', 'v'], ['2', 'a', 'Z', 'v'], ['2', '1', 'Z', 'v'], ['a', '1', 'Z', 'v']] |
Detailed Instructions: In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is "REFERENCE", also write the reference entity, otherwise write the implicit option name. Options to choose from are:
REFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.
YEAR: Describing a calendric year
AGE: Describing someone's age
CURRENCY: Reference to some monetary value e.g dollar, euro etc.
PEOPLE: Describing a single/plural persons
TIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.
OTHER: Some other option, which isn't listed here.
Q: Sam Evans: I did n't mingle very much with the natives .
Victoria Winters: The natives ?
Sam Evans: Yes , that 's , uh , anyone whose family has lived here for at least _ two _ , uh , two hundred or a couple hundred years .
Victoria Winters: Like the Collins family .
Sam Evans: Yeah . You see , they were among the first group to , uh , settle in the area . And it 's the descendants of those people that are the real natives .
Victoria Winters: And where are you from ?
Sam Evans: Connecticut . Well , that 's , uh , pretty far south from here , but , of course , to a real southerner , I 'm a Yankee .
Victoria Winters: Well , to me , you 're just a man I 'm very glad I know .
A: | REFERENCE years |
TASK DEFINITION: You are given an original reference as well as a system generated reference. Your task is to judge the naturaleness of the system generated reference. If the utterance could have been produced by a native speaker output 1, else output 0.
PROBLEM: System Reference: sushi bistro 's address is 431 balboa street.
Original Reference: the address of sushi bistro is 431 balboa street.
SOLUTION: 1
PROBLEM: System Reference: x is a french and continental restaurant in x.
Original Reference: the restaurant x serves french and continental food in the x area.
SOLUTION: 1
PROBLEM: System Reference: x is an italian take-out restaurant that provides takeaway pizza.
Original Reference: x is a takeaway restaurant where you can find italian food.
SOLUTION: | 1
|
Write an incorrect answer to the given question based on the associated fact. You are also provided with the correct answer to the given question. Make sure that your incorrect answer is relevant and similar to the associated fact. Also, try to make the incorrect answer similar to the correct answer so that distinguishing the correct answer from the incorrect answer is not very easy. Make sure you don't accidentally provide another correct answer! Also, make sure they sound reasonable (e.g., might be on a school pop quiz). A good incorrect answer can be constructed using words associated with the question, but not the correct answer. For example, for the question "What helps plants survive?", using words like "weeds", "vase", "bee" (associated with "plant"), or "first aid", "parachute", "accident" (associated with "survive") etc. Your incorrect answers make the question hard, so these results in good incorrect answers.
Let me give you an example: Fact: pesticides can harm animals.
Question: What can harm animals?
Correct Answer: pesticides.
The answer to this example can be: pet shampoo.
Here is why: This is clearly an incorrect answer to the question. And since, it is relevant with the given fact, it is a good incorrect answer. Other good incorrect answers are "fresh water" and "clouds".
OK. solve this:
Fact: Cells divide only a set number of times then experience apoptosis.
Question: Cells divide only a set number of times then experience what?
Correct Answer: apoptosis.
Answer: | dampening. |
Teacher:In this task, you are given a country name and you need to return the region of the world map that the country is located in. The possible regions that are considered valid answers are: Caribbean, Southern Europe, Eastern Europe, Western Europe, South America, North America, Central America, Antarctica, Australia and New Zealand, Central Africa, Northern Africa, Eastern Africa, Western Africa, Southern Africa, Eastern Asia, Southern and Central Asia, Southeast Asia, Middle East, Melanesia, Polynesia, British Isles, Micronesia, Nordic Countries, Baltic Countries.
Teacher: Now, understand the problem? Solve this instance: Liberia
Student: | Western Africa |
Q: The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the elicit-pref strategy, otherwise output No. elicit-pref is a cooperative negotiation strategy. It is used to discover the preference order of the opponent in the negotiation.
Context: 'Just need a little more wood. Then it will be great to cook my dinner on.' 'I got some spare wood. I’m a little short on food though. I didn’t pack enough. ' 'Great, we can split the food, how are you on water?'
Utterance: 'That would be great. I need to have frequent small meals throughout the day so the extra food would help. I have plenty of water. '
A: | No |
Instructions: Given news headlines and an edited word. The original sentence has word within given format {word}. Create new headlines by replacing {word} in the original sentence with edit word. Classify news headlines into "Funny" and "Not Funny" that have been modified by humans using an edit word to make them funny.
Input: News Headline: Donald Trump boasts that his nuclear {button} is bigger than Kim Jong-un 's
Edit: worm
Output: | Funny |
Instructions: Given a sentence in Vietnamese, generate a new Vietnamese sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.
Input: Thời gian được dạy trong trường học.
Output: | Những loại được dạy trong ngôn ngữ. |
In this task, you are provided with an article of the legal acts. Your task is to classify it into three categories (Regulation, Decision and Directive) based on its content: 1) Regulation is a binding legislative act that must be applied in its entirety on a set date across all the member states (European Union countries). 2) Decision is binding on those to whom it is addressed (e.g. an European Union country or an individual company) and is directly applicable. 3) Directive is a legislative act that sets out a goal that all must achieve. However, it is up to the individual countries to devise their own laws on how to reach these goals.
Ex Input:
Decision 78/642/EEC is hereby amended as follows: 1. Article 1 is replaced by the following:'The prohibition provided for in Article 14 (2) of Directive 72/462/EEC shall not apply to the following districts of the Republic of Botswana : Ghanzi (with the exclusion of its north-west sector called 'Ghanzi-Farms'), Kweneng, Kgatlend, South-East, Southern, Kgalagadi or to that part of the country situated between : to the north, Palapye (1)OJ No L 302, 31.12.1972, p. 28. (2)OJ No L 26, 31.1.1977, p. 81. (3)OJ No L 213, 3.8.1978, p. 15. (4)OJ No L 116, 11.5.1979, p. 31.Sherwood Cordon Fence, to the east, the border of the Republic of South Africa, to the south, Dibete Cordon Fence, and to the west, the railway line connecting Dibete and Palapye.'2. In point IV of the animal health certificate set out in the Annex: (a) in the first indent of paragraph 1 (a): - insert after the name 'Ghanzi' the following phrase:'(with the exclusion of its north-western sector known as 'Ghanzi Farms')',- that part of the sentence which reads 'since May 1978 or since birth, have remained in that part of the country to the east of the railway line connecting Dibete and the Rhodesian border' is replaced by the following : 'since May 1978 or since birth, have remained in that part of the country situated between : to the north, Palapye Sherwood Cordon Fence, to the east, the border of the Republic of South Africa, to the south, Dibete Cordon Fence, and to the west, the railway line connecting Dibete and Palapye';(b) in the fourth indent of paragraph 1 (a) that part of the sentence which reads 'and, in the case of animals from that part of the country to the east of the railway line connecting Dibete and the Rhodesian border' is replaced by the following : 'and, in the case of animals from that part of the country between : to the north, Palapye Sherwood Cordon Fence, to the east, the border of the Republic of South Africa, to the south, Dibete Cordon Fence, and to the west, the railway line connecting Dibete and Palapye';(c) the sixth indent of paragraph 1 (a) is replaced by the following : 'were slaughtered after 15 January 1980 (date of slaughter : ...)'. This Decision is addressed to the Member States.
Ex Output:
Decision
Ex Input:
Article 3 (1) (a) and (b) of Regulation (EEC) No 1579/7A is replaced by the following:‘(a) In the case referred to in the preceding subparagraph, and except in respect of products falling within subheading 23.07 B specified in Annex A of Regulation No 120/67/EEC any adjustment of the levy shall subject to the operation of the second subparagraph of Article 15 (3) of Regulation No 120/67/EEC, be made in relation to the threshold price for the basic product or products used for the purpose of calculating the variable component of the levy operative on the day of importation. Such adjustment shall be made by increasing or reducing the levy which was fixed in advance by the difference between the threshold price for 100 kg of the basic product operative for the month in which the application is made and that operative for the month of importation, that difference being multiplied by the coefficient shown in column 4 of the Annex to Regulation (EEC) No 1052/68.(b) With regard to the products referred to in Article 2, the levy fixed in advance shall moreover be adjusted if the production refunds fixed in Article 1 of Regulation (EEC) No 1955/75 are altered between the day on which the licence is applied for and the day of importation. Such adjustment shall be made by increasing or decreasing the amount of levy fixed in advance by reference to the difference resulting from such alteration, that difference being multiplied by the coefficient shown in column 4 of the Annex to Regulation (EEC) No 1052/68 against the products in question.’ This Regulation shall enter into force on 1 August 1975.This Regulation shall be binding in its entirety and directly applicable in all Member States.
Ex Output:
Regulation
Ex Input:
Section 'A. Standard gross margins' of Annex I to Decision 78/463/EEC is amended as follows: 1. the following sentence is added to the last paragraph:'; the SGM for Greece are regionalized at the level of 15 nomos groups.'2. the following conversion rate is added to footnote (1):', 35 73081 drachmas.'3. the SGMs for Greece set out in the Annex hereto are added to the SGMs for the Member States. This Decision shall enter into force on 1 January 1981. This Decision is addressed to the Member States.
Ex Output:
| Decision
|
You will be given a definition of a task first, then some input of the task.
In this task you will be given two lists of numbers and you need to calculate the intersection between these two lists. The intersection between two lists is another list where every element is common between the two original lists. If there are no elements in the intersection, answer with an empty list. Your list of numbers must be inside brackets. Sort the numbers in your answer in an ascending order, that is, no matter what the order of the numbers in the lists is, you should put them in your answer in an ascending order.
[4, 9, 1, 6, 1, 2, 8, 1, 1, 8] , [2, 1, 4, 6, 7, 1, 3, 5, 2, 7]
Output: | [1, 2, 4, 6] |
A text is given in Hindi. Translate it from the Hindi language to the Oriya language. The translation must not omit or add information to the original sentence.
उन्होने यह भी कहा कि नौसेना समुद्री क्षेत्र में राष्ट्रीय हितों की सुरक्षा, संवर्धन और संरक्षण के लिये सदैव तैयार है।
ପ୍ରଧାନମନ୍ତ୍ରୀ ଶ୍ରୀ ନରେନ୍ଦ୍ର ମୋଦୀଙ୍କ ଅଧ୍ୟକ୍ଷତାରେ ଅନୁଷ୍ଠିତ କେନ୍ଦ୍ର କ୍ୟାବିନେଟ୍ ବୈଠକରେ 17 ମାର୍ଚ୍ଚ 2019ରେ ମୁଖ୍ୟମନ୍ତ୍ରୀ ଶ୍ରୀ ମନୋହର ପାରିକରଙ୍କ ଦୁଃଖଦ ବିୟୋଗରେ ଶୋକ ପ୍ରକାଶ କରାଯାଇଛି । ସ୍ୱର୍ଗତ ମନୋହର ପାରିକରଙ୍କ ସ୍ମୃତିରେ କ୍ୟାବିନେଟରେ ଦୁଇ ମିନିଟ ନିରବ ପ୍ରାର୍ଥନା କରାଯାଇଥିଲା ।
मैं नहीं मानता हूं गरीब का, गरीब से गरीब 90 पैसे खर्च नहीं कर सकता है।
ବାବୁମାନଙ୍କୁ କାମର ଉତ୍ତର ଦେବାକୁ ପଡ଼ିବ କି ପଡ଼ିବ ନାହିଁ? ଗୋଟିଏ-ଗୋଟିଏ ପଇସାର ହିସାବ ଦେବାକୁ ପଡ଼ିବ କି ପଡ଼ିବ ନାହିଁ?
आयोजन के तहत निर्यात-आधारित निर्माण और दक्षिण एवं दक्षिण-पूर्व एशिया की उभरती हुई अर्थव्यवस्थाओं को सेवाओं के संबंध में राज्य द्वारा प्रदान किए जाने वाले अवसरों का ब्यौरा उपलब्ध किया जाएगा।
| ଗଣତାନ୍ତ୍ରିକ ପଦ୍ଧତିରେ ଅନୁଷ୍ଠିତ ହେଉଥିବା ନିର୍ବାଚନରେ ଅଂଶ ଗ୍ରହଣ କରିବାକୁ ନାଗାଲାଣ୍ଡର ଲୋକମାନଙ୍କୁ କେନ୍ଦ୍ର ସ୍ୱରାଷ୍ଟ୍ର ରାଷ୍ଟ୍ରମନ୍ତ୍ରୀ କିରେନ୍ ରିଜିଜୁ ଅନୁରୋଧ କରିଛନ୍ତି । ନାଗାଲାଣ୍ଡର ଲୋକଙ୍କୁ ଏକ ବାର୍ତ୍ତାରେ ସେ କହିଛନ୍ତି, ନାଗା ଲୋକଙ୍କ ଆବେଗ ସହ କେନ୍ଦ୍ର ସରକାର ଅବଗତ ଅଛନ୍ତି । ସେମାନଙ୍କ ସମସ୍ୟାର ସମାଧାନ ପାଇଁ ସରକାର ପ୍ରତିଶ୍ରୁତିବଦ୍ଧ । ସମାଧାନର ଉପାୟ ଯଥାଶୀଘ୍ର ଲାଗୁ କରିବାକୁ ସରକାର ଉଦ୍ୟମ କରୁଛନ୍ତି ।
|
You are given a list of integers and an integer target, return a list of a pair of numbers in any order such that they add up to target. If there is no such pair of numbers, then return an empty list
[45, 6, 5, 17, 23, 29, 20, 46, 30, 37, 13, 35, 38, 40, 36, 10, 49, 15, 44, 24], target=30 | [17, 13] |
Subsets and Splits