Improving Distantly-supervised Entity Typing with Compact Latent Space Clustering

Bo Chen, Xiaotao Gu, Yufeng Hu, Siliang Tang, Guoping Hu, Yueting Zhuang, Xiang Ren


Abstract
Recently, distant supervision has gained great success on Fine-grained Entity Typing (FET). Despite its efficiency in reducing manual labeling efforts, it also brings the challenge of dealing with false entity type labels, as distant supervision assigns labels in a context-agnostic manner. Existing works alleviated this issue with partial-label loss, but usually suffer from confirmation bias, which means the classifier fit a pseudo data distribution given by itself. In this work, we propose to regularize distantly supervised models with Compact Latent Space Clustering (CLSC) to bypass this problem and effectively utilize noisy data yet. Our proposed method first dynamically constructs a similarity graph of different entity mentions; infer the labels of noisy instances via label propagation. Based on the inferred labels, mention embeddings are updated accordingly to encourage entity mentions with close semantics to form a compact cluster in the embedding space, thus leading to better classification performance. Extensive experiments on standard benchmarks show that our CLSC model consistently outperforms state-of-the-art distantly supervised entity typing systems by a significant margin.
Anthology ID:
N19-1294
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2862–2872
Language:
URL:
https://aclanthology.org/N19-1294
DOI:
10.18653/v1/N19-1294
Bibkey:
Cite (ACL):
Bo Chen, Xiaotao Gu, Yufeng Hu, Siliang Tang, Guoping Hu, Yueting Zhuang, and Xiang Ren. 2019. Improving Distantly-supervised Entity Typing with Compact Latent Space Clustering. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2862–2872, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Improving Distantly-supervised Entity Typing with Compact Latent Space Clustering (Chen et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1294.pdf
Data
FIGER