You are provided with a paragraph. Your goal is to automatically identify the…
- User
System: You are provided with a paragraph. Your goal is to automatically identify the most relevant tasks based on the content of the paragraph and generate an example of entailment (if the task conclusion can be logically inferred from the paragraph) and a different example of non-entailment (if it is unclear or the opposite conclusion is true).
Step 1: Read the paragraph carefully. Step 2: Automatically decide which tasks are relevant based on the paragraph’s content. Relevant tasks may include, but are not limited to: - Topic Classification - Risk Classification - Sentiment Classification - Tone Classification - Event Detection - Entity Recognition - Geographical Recognition - Trend Detection - Intent Detection - Sector Identification - Impact Classification - Tense Identification (Past, Present, Future) - Uncertainty Identification
Step 3: For each relevant task you identify, generate two clear and concise examples whose labels match common practices for the task at hand: one for entailment and one for non-entailment. The example should speak about the text at the 3rd person. Step 4: Output the results in the following JSON format:
{ 'relevant_tasks': [ { 'task': , 'examples': [ { 'input': , 'label': 'entailment', }, { 'input': <The non-entailment example (neutral or contradiction) based on the paragraph>, 'label': 'non-entailment', } ] }, ... ] } User: Pfizer now says its coronavirus vaccine is effective in preventing Covid in children over age 12. Middle school students could be eligible for the shots before the fall. The National Parents Union worries this could delay reopening schools in the spring. Getting kids vaccinated could go a long way Assistant:
- Assistant
{ 'relevant_tasks': [ { 'task': 'Topic Classification', 'examples': [ { 'input': 'The paragraph talks about vaccination against Covid-19 for children.', 'label': 'entailment', }, { 'input': 'The paragraph discusses economic policies in relation to Covid-19.', 'label': 'non-entailment', } ] }, { 'task': 'Sentiment Classification', 'examples': [ { 'input': 'The sentiment in the paragraph reflects optimism due to the effectiveness of the vaccine for children.', 'label': 'entailment', }, { 'input': 'The sentiment in the paragraph is negative and focuses on the adverse effects of the vaccine.', 'label': 'non-entailment', } ] }, { 'task': 'Event Detection', 'examples': [ { 'input': 'The announcement by Pfizer about its vaccine efficacy in children over age 12 is an event in the paragraph.', 'label': 'entailment', }, { 'input': 'The paragraph describes an event of launching a new educational policy.', 'label': 'non-entailment', } ] }, { 'task': 'Entity Recognition', 'examples': [ { 'input': 'Pfizer and National Parents Union are entities mentioned in the paragraph.', 'label': 'entailment', }, { 'input': 'The paragraph mentions the entity World Health Organization.', 'label': 'non-entailment', } ] }, { 'task': 'Tense Identification', 'examples': [ { 'input': 'The tense of the paragraph includes present and future aspects.', 'label': 'entailment', }, { 'input': 'The paragraph is written entirely in the past tense.', 'label': 'non-entailment', } ] }, { 'task': 'Impact Classification', 'examples': [ { 'input': 'The impact described relates to potential eligibility for vaccinations and school reopening concerns.', 'label': 'entailment', }, { 'input': 'The paragraph emphasizes the impact of economic instability due to the pandemic.', 'label': 'non-entailment', } ] } ] }