Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction

Quzhe Huang, Shengqi Zhu, Yansong Feng, Yuan Ye, Yuxuan Lai, Dongyan Zhao


Abstract
Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences. Yet, human annotators usually use a small number of sentences to identify the relationship between a given entity pair. In this paper, we present an embarrassingly simple but effective method to heuristically select evidence sentences for document-level RE, which can be easily combined with BiLSTM to achieve good performance on benchmark datasets, even better than fancy graph neural network based methods. We have released our code at https://github.com/AndrewZhe/Three-Sentences-Are-All-You-Need.
Anthology ID:
2021.acl-short.126
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
998–1004
Language:
URL:
https://aclanthology.org/2021.acl-short.126
DOI:
10.18653/v1/2021.acl-short.126
Bibkey:
Cite (ACL):
Quzhe Huang, Shengqi Zhu, Yansong Feng, Yuan Ye, Yuxuan Lai, and Dongyan Zhao. 2021. Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 998–1004, Online. Association for Computational Linguistics.
Cite (Informal):
Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction (Huang et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.126.pdf
Video:
 https://aclanthology.org/2021.acl-short.126.mp4
Data
DocRED