Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction

Junyoung Son, Jinsung Kim, Jungwoo Lim, Yoonna Jang, Heuiseok Lim


Abstract
Cross-document relation extraction (CodRED) task aims to infer the relation between two entities mentioned in different documents within a reasoning path. Previous studies have concentrated on merely capturing implicit relations between the entities. However, humans usually utilize explicit information chains such as hyperlinks or additional searches to find the relations between two entities. Inspired by this, we propose Path wIth expLOraTion (PILOT) that provides the enhanced reasoning path by exploring the explicit clue information within the documents. PILOT finds the bridging entities which directly guide the paths between the entities and then employs them as stepstones to navigate desirable paths. We show that models with PILOT outperform the baselines in the CodRED task. Furthermore, we offer a variety of analyses to verify the validity of the reasoning paths constructed through PILOT, including evaluations using large language models such as ChatGPT.
Anthology ID:
2023.findings-emnlp.450
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6755–6761
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.450
DOI:
10.18653/v1/2023.findings-emnlp.450
Bibkey:
Cite (ACL):
Junyoung Son, Jinsung Kim, Jungwoo Lim, Yoonna Jang, and Heuiseok Lim. 2023. Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6755–6761, Singapore. Association for Computational Linguistics.
Cite (Informal):
Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction (Son et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.450.pdf