Multi-hop Evidence Retrieval for Cross-document Relation Extraction
Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen
Abstract
Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document. This inevitably brings the challenge of efficient open-space evidence retrieval to support the inference of cross-document relations,along with the challenge of multi-hop reasoning on top of entities and evidence scattered in an open set of documents. To combat these challenges, we propose Mr.Cod (Multi-hop evidence retrieval for Cross-document relation extraction), which is a multi-hop evidence retrieval method based on evidence path mining and ranking. We explore multiple variants of retrievers to show evidence retrieval is essential in cross-document RE.We also propose a contextual dense retriever for this setting. Experiments on CodRED show that evidence retrieval with Mr.Cod effectively acquires cross-document evidence and boosts end-to-end RE performance in both closed and open settings.- Anthology ID:
- 2023.findings-acl.657
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 10336–10351
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.657
- DOI:
- 10.18653/v1/2023.findings-acl.657
- Cite (ACL):
- Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, and Muhao Chen. 2023. Multi-hop Evidence Retrieval for Cross-document Relation Extraction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 10336–10351, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Multi-hop Evidence Retrieval for Cross-document Relation Extraction (Lu et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2023.findings-acl.657.pdf