arXiv:2110.00479
Learning to Ask for Data-Efficient Event Argument Extraction
원문 초록
Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles. In this study, we cast EAE as a question-based cloze task and empirically analyze fixed discrete token template performance. As generating human-annotated question templates is often time-consuming and labor-intensive, we further propose a novel approach called "Learning to Ask," which can learn optimized question templates for EAE without human annotations. Experiments using the ACE-2005 dataset demonstrate that our method based on optimized questions achieves state-of-the-art performance in both the few-shot and supervised settings.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
One Small and One Large for Document-level Event Argument Extraction
Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction
Small Models Are (Still) Effective Cross-Domain Argument Extractors
Constrained Decoding for Cross-lingual Label Projection
MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation
LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.