Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing

Wenhan Xiong, Jiawei Wu, Deren Lei, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang


Abstract
Existing entity typing systems usually exploit the type hierarchy provided by knowledge base (KB) schema to model label correlations and thus improve the overall performance. Such techniques, however, are not directly applicable to more open and practical scenarios where the type set is not restricted by KB schema and includes a vast number of free-form types. To model the underlying label correlations without access to manually annotated label structures, we introduce a novel label-relational inductive bias, represented by a graph propagation layer that effectively encodes both global label co-occurrence statistics and word-level similarities. On a large dataset with over 10,000 free-form types, the graph-enhanced model equipped with an attention-based matching module is able to achieve a much higher recall score while maintaining a high-level precision. Specifically, it achieves a 15.3% relative F1 improvement and also less inconsistency in the outputs. We further show that a simple modification of our proposed graph layer can also improve the performance on a conventional and widely-tested dataset that only includes KB-schema types.
Anthology ID:
N19-1084
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:
773–784
Language:
URL:
https://aclanthology.org/N19-1084
DOI:
10.18653/v1/N19-1084
Bibkey:
Cite (ACL):
Wenhan Xiong, Jiawei Wu, Deren Lei, Mo Yu, Shiyu Chang, Xiaoxiao Guo, and William Yang Wang. 2019. Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing. 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 773–784, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing (Xiong et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1084.pdf
Code
 xwhan/Extremely-Fine-Grained-Entity-Typing
Data
OntoNotes 5.0Open Entity