A Simple Model for Distantly Supervised Relation Extraction

Ziqin Rao, Fangxiang Feng, Ruifan Li, Xiaojie Wang


Abstract
Distantly supervised relation extraction is challenging due to the noise within data. Recent methods focus on exploiting bag representations based on deep neural networks with complex de-noising scheme to achieve remarkable performance. In this paper, we propose a simple but effective BERT-based Graph convolutional network Model (i.e., BGM). Our BGM comprises of an instance embedding module and a bag representation module. The instance embedding module uses a BERT-based pretrained language model to extract key information from each instance. The bag representaion module constructs the corresponding bag graph then apply a convolutional operation to obtain the bag representation. Our BGM model achieves a considerable improvement on two benchmark datasets, i.e., NYT10 and GDS.
Anthology ID:
2022.coling-1.234
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2651–2657
Language:
URL:
https://aclanthology.org/2022.coling-1.234
DOI:
Bibkey:
Cite (ACL):
Ziqin Rao, Fangxiang Feng, Ruifan Li, and Xiaojie Wang. 2022. A Simple Model for Distantly Supervised Relation Extraction. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2651–2657, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
A Simple Model for Distantly Supervised Relation Extraction (Rao et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.234.pdf