Double Graph Based Reasoning for Document-level Relation Extraction

Shuang Zeng, Runxin Xu, Baobao Chang, Lei Li


Abstract
Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across paragraphs. In this paper, we propose Graph Aggregation-and-Inference Network (GAIN), a method to recognize such relations for long paragraphs. GAIN constructs two graphs, a heterogeneous mention-level graph (MG) and an entity-level graph (EG). The former captures complex interaction among different mentions and the latter aggregates mentions underlying for the same entities. Based on the graphs we propose a novel path reasoning mechanism to infer relations between entities. Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art. Our code is available at https://github.com/PKUnlp-icler/GAIN.
Anthology ID:
2020.emnlp-main.127
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1630–1640
Language:
URL:
https://aclanthology.org/2020.emnlp-main.127
DOI:
10.18653/v1/2020.emnlp-main.127
Bibkey:
Cite (ACL):
Shuang Zeng, Runxin Xu, Baobao Chang, and Lei Li. 2020. Double Graph Based Reasoning for Document-level Relation Extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1630–1640, Online. Association for Computational Linguistics.
Cite (Informal):
Double Graph Based Reasoning for Document-level Relation Extraction (Zeng et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.emnlp-main.127.pdf
Video:
 https://slideslive.com/38938659
Code
 DreamInvoker/GAIN +  additional community code
Data
DocRED