Novel Relation Detection: Discovering Unknown Relation Types via Multi-Strategy Self-Supervised Learning
Qingbin Liu, Yin Kung, Yanchao Hao, Dianbo Sui, Siyuan Cheng, Xi Chen, Ningyu Zhang, Jiaoyan Chen
Abstract
Conventional approaches to relation extraction can only recognize predefined relation types. In the real world, new or out-of-scope relation types may keep challenging the deployed models. In this paper, we formalize such a challenging problem as Novel Relation Detection (NRD), which aims to discover potential new relation types based on training samples of known relations. To this end, we construct two NRD datasets and exhaustively investigate a variety of out-of-scope detection methods. We further propose an effective NRD method that utilizes multi-strategy self-supervised learning to handle the problem of shallow semantic similarity in the NRD task. Experimental results demonstrate the effectiveness of our method, which significantly outperforms previous state-of-the-art methods on both datasets.- Anthology ID:
- 2023.findings-emnlp.211
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3204–3214
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.211
- DOI:
- 10.18653/v1/2023.findings-emnlp.211
- Cite (ACL):
- Qingbin Liu, Yin Kung, Yanchao Hao, Dianbo Sui, Siyuan Cheng, Xi Chen, Ningyu Zhang, and Jiaoyan Chen. 2023. Novel Relation Detection: Discovering Unknown Relation Types via Multi-Strategy Self-Supervised Learning. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3204–3214, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Novel Relation Detection: Discovering Unknown Relation Types via Multi-Strategy Self-Supervised Learning (Liu et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/landing_page/2023.findings-emnlp.211.pdf