%0 Conference Proceedings %T Contextualized context2vec %A Ashihara, Kazuki %A Kajiwara, Tomoyuki %A Arase, Yuki %A Uchida, Satoru %Y Xu, Wei %Y Ritter, Alan %Y Baldwin, Tim %Y Rahimi, Afshin %S Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019) %D 2019 %8 November %I Association for Computational Linguistics %C Hong Kong, China %F ashihara-etal-2019-contextualized %X Lexical substitution ranks substitution candidates from the viewpoint of paraphrasability for a target word in a given sentence. There are two major approaches for lexical substitution: (1) generating contextualized word embeddings by assigning multiple embeddings to one word and (2) generating context embeddings using the sentence. Herein we propose a method that combines these two approaches to contextualize word embeddings for lexical substitution. Experiments demonstrate that our method outperforms the current state-of-the-art method. We also create CEFR-LP, a new evaluation dataset for the lexical substitution task. It has a wider coverage of substitution candidates than previous datasets and assigns English proficiency levels to all target words and substitution candidates. %R 10.18653/v1/D19-5552 %U https://aclanthology.org/D19-5552 %U https://doi.org/10.18653/v1/D19-5552 %P 397-406