Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering

Zimu Wang, Lei Xia, Wei Wang Xjtlu, Xinya Du

Abstract
As an essential task in information extraction (IE), Event-Event Causal Relation Extraction (ECRE) aims to identify and classify the causal relationships between event mentions in natural language texts. However, existing research on ECRE has highlighted two critical challenges, including the lack of document-level modeling and causal hallucinations. In this paper, we propose a Knowledge-guided binary Question Answering (KnowQA) method with event structures for ECRE, consisting of two stages: Event Structure Construction and Binary Question Answering. We conduct extensive experiments under both zero-shot and fine-tuning settings with large language models (LLMs) on the MECI and MAVEN-ERE datasets. Experimental results demonstrate the usefulness of event structures on document-level ECRE and the effectiveness of KnowQA by achieving state-of-the-art on the MECI dataset. We observe not only the effectiveness but also the high generalizability and low inconsistency of our method, particularly when with complete event structures after fine-tuning the models.
Anthology ID:
2024.findings-emnlp.986
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16944–16955
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.986/
DOI:
10.18653/v1/2024.findings-emnlp.986
Bibkey:
Cite (ACL):
Zimu Wang, Lei Xia, Wei Wang Xjtlu, and Xinya Du. 2024. Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16944–16955, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering (Wang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.986.pdf
PDF Search