Learning to Bootstrap for Entity Set Expansion

Lingyong Yan, Xianpei Han, Le Sun, Ben He


Abstract
Bootstrapping for Entity Set Expansion (ESE) aims at iteratively acquiring new instances of a specific target category. Traditional bootstrapping methods often suffer from two problems: 1) delayed feedback, i.e., the pattern evaluation relies on both its direct extraction quality and extraction quality in later iterations. 2) sparse supervision, i.e., only few seed entities are used as the supervision. To address the above two problems, we propose a novel bootstrapping method combining the Monte Carlo Tree Search (MCTS) algorithm with a deep similarity network, which can efficiently estimate delayed feedback for pattern evaluation and adaptively score entities given sparse supervision signals. Experimental results confirm the effectiveness of the proposed method.
Anthology ID:
D19-1028
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
292–301
Language:
URL:
https://aclanthology.org/D19-1028
DOI:
10.18653/v1/D19-1028
Bibkey:
Cite (ACL):
Lingyong Yan, Xianpei Han, Le Sun, and Ben He. 2019. Learning to Bootstrap for Entity Set Expansion. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 292–301, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Learning to Bootstrap for Entity Set Expansion (Yan et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/D19-1028.pdf