A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents

Tapas Nayak, Hwee Tou Ng


Abstract
Distantly supervised datasets for relation extraction mostly focus on sentence-level extraction, and they cover very few relations. In this work, we propose cross-document relation extraction, where the two entities of a relation tuple appear in two different documents that are connected via a chain of common entities. Following this idea, we create a dataset for two-hop relation extraction, where each chain contains exactly two documents. Our proposed dataset covers a higher number of relations than the publicly available sentence-level datasets. We also propose a hierarchical entity graph convolutional network (HEGCN) model for this task that improves performance by 1.1% F1 score on our two-hop relation extraction dataset, compared to some strong neural baselines.
Anthology ID:
2021.ranlp-1.115
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
1022–1030
Language:
URL:
https://aclanthology.org/2021.ranlp-1.115
DOI:
Bibkey:
Cite (ACL):
Tapas Nayak and Hwee Tou Ng. 2021. A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1022–1030, Held Online. INCOMA Ltd..
Cite (Informal):
A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents (Nayak & Ng, RANLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ranlp-1.115.pdf
Code
 nusnlp/MHRE
Data
THREDDocREDFewRel 2.0WikiHop