From Learning-to-Match to Learning-to-Discriminate:Global Prototype Learning for Few-shot Relation Classification
Liu Fangchao, Xiao Xinyan, Yan Lingyong, Lin Hongyu, Han Xianpei, Dai Dai, Wu Hua, Sun Le
Abstract
Few-shot relation classification has attracted great attention recently and is regarded as an ef-fective way to tackle the long-tail problem in relation classification. Most previous works onfew-shot relation classification are based on learning-to-match paradigms which focus on learn-ing an effective universal matcher between the query and one target class prototype based oninner-class support sets. However the learning-to-match paradigm focuses on capturing the sim-ilarity knowledge between query and class prototype while fails to consider discriminative infor-mation between different candidate classes. Such information is critical especially when targetclasses are highly confusing and domain shifting exists between training and testing phases. Inthis paper we propose the Global Transformed Prototypical Networks(GTPN) which learns tobuild a few-shot model to directly discriminate between the query and all target classes with bothinner-class local information and inter-class global information. Such learning-to-discriminate paradigm can make the model concentrate more on the discriminative knowledge between allcandidate classes and therefore leads to better classification performance. We conducted exper-iments on standard FewRel benchmarks. Experimental results show that GTPN achieves very competitive performance on few-shot relation classification and reached the best performance onthe official leaderboard of FewRel 2.0 1.- Anthology ID:
- 2021.ccl-1.90
- Volume:
- Proceedings of the 20th Chinese National Conference on Computational Linguistics
- Month:
- August
- Year:
- 2021
- Address:
- Huhhot, China
- Editors:
- Sheng Li (李生), Maosong Sun (孙茂松), Yang Liu (刘洋), Hua Wu (吴华), Kang Liu (刘康), Wanxiang Che (车万翔), Shizhu He (何世柱), Gaoqi Rao (饶高琦)
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 1012–1023
- Language:
- English
- URL:
- https://aclanthology.org/2021.ccl-1.90
- DOI:
- Cite (ACL):
- Liu Fangchao, Xiao Xinyan, Yan Lingyong, Lin Hongyu, Han Xianpei, Dai Dai, Wu Hua, and Sun Le. 2021. From Learning-to-Match to Learning-to-Discriminate:Global Prototype Learning for Few-shot Relation Classification. In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 1012–1023, Huhhot, China. Chinese Information Processing Society of China.
- Cite (Informal):
- From Learning-to-Match to Learning-to-Discriminate:Global Prototype Learning for Few-shot Relation Classification (Fangchao et al., CCL 2021)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2021.ccl-1.90.pdf
- Data
- FewRel, FewRel 2.0