BERT-based Lexical Substitution

Published in The 57th annual meeting of the Association for Computational Linguistics. (ACL, 2019), 2019

Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou

We proposed a novel lexical substitution based on pretrained masked lanuage models (e.g. BERT) to automatically propose substitute candidates and rank them without relying on external lexical resources.

PDF

Recommended citation: “@inproceedings{zhou2019bert, title={BERT-based Lexical Substitution}, author={Zhou, Wangchunshu and Ge, Tao and Xu, Ke and Wei, Furu and Zhou, Ming}, booktitle={Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, pages={3368–3373}, year={2019} }”.