Abstract
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-short text classification. The model develops a dynamic routing mechanism over static memory, enabling it to better adapt to unseen classes, a critical capability for few-short classification. The model also expands the induction process with supervised learning weights and query information to enhance the generalization ability of meta-learning. The proposed model brings forward the state-of-the-art performance significantly by 2~4% improvement on the miniRCV1 and ODIC datasets. Detailed analysis is further performed to show how the proposed network achieves the new performance.- Anthology ID:
- 2020.acl-main.102
- 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:
- 1087–1094
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.102
- DOI:
- 10.18653/v1/2020.acl-main.102
- Cite (ACL):
- Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, and Xiaodan Zhu. 2020. Dynamic Memory Induction Networks for Few-Shot Text Classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1087–1094, Online. Association for Computational Linguistics.
- Cite (Informal):
- Dynamic Memory Induction Networks for Few-Shot Text Classification (Geng et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.acl-main.102.pdf