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: Andrew Left, an American short-seller banned from trading in Hong Kong for a damning report he wrote on Evergrande, says the Chinese property developer's debt crisis was "a long time coming." Left told CNBC the Evergrande crisis is not a "Lehman moment" for China, and said he doesn't think Evergr Assistant:
- Assistant
{ 'relevant_tasks': [ { 'task': 'Topic Classification', 'examples': [ { 'input': 'The paragraph discusses the debt crisis of the Chinese property developer Evergrande.', 'label': 'entailment' }, { 'input': 'The paragraph is primarily about advancements in renewable energy technologies.', 'label': 'non-entailment' } ] }, { 'task': 'Event Detection', 'examples': [ { 'input': 'The paragraph describes an event involving a crisis faced by Evergrande.', 'label': 'entailment' }, { 'input': 'The paragraph describes the launch of a new product by Evergrande.', 'label': 'non-entailment' } ] }, { 'task': 'Risk Classification', 'examples': [ { 'input': 'The paragraph indicates significant financial risk for the Chinese property market due to Evergrande’s crisis.', 'label': 'entailment' }, { 'input': 'The paragraph suggests the Evergrande situation poses no risk to financial markets.', 'label': 'non-entailment' } ] }, { 'task': 'Tense Identification', 'examples': [ { 'input': 'The paragraph uses the past tense when referring to Andrew Left’s report on Evergrande.', 'label': 'entailment' }, { 'input': 'The paragraph exclusively uses future tense to describe events.', 'label': 'non-entailment' } ] }, { 'task': 'Tone Classification', 'examples': [ { 'input': 'The tone of the paragraph is cautionary as it discusses the Evergrande crisis.', 'label': 'entailment' }, { 'input': 'The tone of the paragraph is optimistic about Evergrande’s future success.', 'label': 'non-entailment' } ] }, { 'task': 'Uncertainty Identification', 'examples': [ { 'input': 'The paragraph expresses uncertainty about the severity of the impact of the Evergrande crisis.', 'label': 'entailment' }, { 'input': 'The paragraph provides absolute certainty about Evergrande’s impact being negligible.', 'label': 'non-entailment' } ] } ] }