Entity-centered Cross-document Relation Extraction

Fengqi Wang, Fei Li, Hao Fei, Jingye Li, Shengqiong Wu, Fangfang Su, Wenxuan Shi, Donghong Ji, Bo Cai


Abstract
Relation Extraction (RE) is a fundamental task of information extraction, which has attracted a large amount of research attention. Previous studies focus on extracting the relations within a sentence or document, while currently researchers begin to explore cross-document RE. However, current cross-document RE methods directly utilize text snippets surrounding target entities in multiple given documents, which brings considerable noisy and non-relevant sentences. Moreover, they utilize all the text paths in a document bag in a coarse-grained way, without considering the connections between these text paths.In this paper, we aim to address both of these shortages and push the state-of-the-art for cross-document RE. First, we focus on input construction for our RE model and propose an entity-based document-context filter to retain useful information in the given documents by using the bridge entities in the text paths. Second, we propose a cross-document RE model based on cross-path entity relation attention, which allow the entity relations across text paths to interact with each other. We compare our cross-document RE method with the state-of-the-art methods in the dataset CodRED. Our method outperforms them by at least 10% in F1, thus demonstrating its effectiveness.
Anthology ID:
2022.emnlp-main.671
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9871–9881
Language:
URL:
https://aclanthology.org/2022.emnlp-main.671
DOI:
10.18653/v1/2022.emnlp-main.671
Bibkey:
Cite (ACL):
Fengqi Wang, Fei Li, Hao Fei, Jingye Li, Shengqiong Wu, Fangfang Su, Wenxuan Shi, Donghong Ji, and Bo Cai. 2022. Entity-centered Cross-document Relation Extraction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9871–9881, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Entity-centered Cross-document Relation Extraction (Wang et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2022.emnlp-main.671.pdf
Software:
 2022.emnlp-main.671.software.zip