QA-SRL
Introduced by He et al. in Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language
QA-SRL was proposed as an open schema for semantic roles, in which the relation between an argument and a predicate is expressed as a natural-language question containing the predicate (“Where was someone educated?”) whose answer is the argument (“Princeton”). The authors collected about 19,000 question-answer pairs from 3,200 sentences.
Source: Zero-Shot Relation Extraction via Reading ComprehensionPapers
| Paper | Code | Results | Date | Stars |
|---|
