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
- 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)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2020.emnlp-main.299.pdf
- Code
- THU-BPM/SelfORE
- Data
- New York Times Annotated Corpus, T-REx