Global-to-Local Neural Networks for Document-Level Relation Extraction

Difeng Wang, Wei Hu, Ermei Cao, Weijian Sun


Abstract
Relation extraction (RE) aims to identify the semantic relations between named entities in text. Recent years have witnessed it raised to the document level, which requires complex reasoning with entities and mentions throughout an entire document. In this paper, we propose a novel model to document-level RE, by encoding the document information in terms of entity global and local representations as well as context relation representations. Entity global representations model the semantic information of all entities in the document, entity local representations aggregate the contextual information of multiple mentions of specific entities, and context relation representations encode the topic information of other relations. Experimental results demonstrate that our model achieves superior performance on two public datasets for document-level RE. It is particularly effective in extracting relations between entities of long distance and having multiple mentions.
Anthology ID:
2020.emnlp-main.303
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3711–3721
Language:
URL:
https://aclanthology.org/2020.emnlp-main.303
DOI:
10.18653/v1/2020.emnlp-main.303
Bibkey:
Cite (ACL):
Difeng Wang, Wei Hu, Ermei Cao, and Weijian Sun. 2020. Global-to-Local Neural Networks for Document-Level Relation Extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3711–3721, Online. Association for Computational Linguistics.
Cite (Informal):
Global-to-Local Neural Networks for Document-Level Relation Extraction (Wang et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.303.pdf
Optional supplementary material:
 2020.emnlp-main.303.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38938684
Code
 nju-websoft/GLRE
Data
DocRED