Abstract
Hypernymy detection, a.k.a, lexical entailment, is a fundamental sub-task of many natural language understanding tasks. Previous explorations mostly focus on monolingual hypernymy detection on high-resource languages, e.g., English, but few investigate the low-resource scenarios. This paper addresses the problem of low-resource hypernymy detection by combining high-resource languages. We extensively compare three joint training paradigms and for the first time propose applying meta learning to relieve the low-resource issue. Experiments demonstrate the superiority of our method among the three settings, which substantially improves the performance of extremely low-resource languages by preventing over-fitting on small datasets.- Anthology ID:
- 2020.acl-main.336
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3651–3656
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.336
- DOI:
- 10.18653/v1/2020.acl-main.336
- Cite (ACL):
- Changlong Yu, Jialong Han, Haisong Zhang, and Wilfred Ng. 2020. Hypernymy Detection for Low-Resource Languages via Meta Learning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3651–3656, Online. Association for Computational Linguistics.
- Cite (Informal):
- Hypernymy Detection for Low-Resource Languages via Meta Learning (Yu et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.acl-main.336.pdf