SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction

Xuming Hu, Lijie Wen, Yusong Xu, Chenwei Zhang, Philip Yu


Abstract
Open relation extraction is the task of extracting open-domain relation facts from natural language sentences. Existing works either utilize heuristics or distant-supervised annotations to train a supervised classifier over pre-defined relations, or adopt unsupervised methods with additional assumptions that have less discriminative power. In this work, we propose a self-supervised framework named SelfORE, which exploits weak, self-supervised signals by leveraging large pretrained language model for adaptive clustering on contextualized relational features, and bootstraps the self-supervised signals by improving contextualized features in relation classification. Experimental results on three datasets show the effectiveness and robustness of SelfORE on open-domain Relation Extraction when comparing with competitive baselines.
Anthology ID:
2020.emnlp-main.299
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:
3673–3682
Language:
URL:
https://aclanthology.org/2020.emnlp-main.299
DOI:
10.18653/v1/2020.emnlp-main.299
Bibkey:
Cite (ACL):
Xuming Hu, Lijie Wen, Yusong Xu, Chenwei Zhang, and Philip Yu. 2020. SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3673–3682, Online. Association for Computational Linguistics.
Cite (Informal):
SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction (Hu et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2020.emnlp-main.299.pdf
Video:
 https://slideslive.com/38938930
Code
 THU-BPM/SelfORE
Data
New York Times Annotated CorpusT-REx