Contextualized context2vec

Kazuki Ashihara, Tomoyuki Kajiwara, Yuki Arase, Satoru Uchida

Abstract
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.
Anthology ID:
D19-5552
Volume:
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
397–406
Language:
URL:
https://aclanthology.org/D19-5552
DOI:
10.18653/v1/D19-5552
Bibkey:
Cite (ACL):
Kazuki Ashihara, Tomoyuki Kajiwara, Yuki Arase, and Satoru Uchida. 2019. Contextualized context2vec. In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019), pages 397–406, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Contextualized context2vec (Ashihara et al., WNUT 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/D19-5552.pdf
PDF Search