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
Venues:
EMNLP | WNUT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
397–406
Language:
URL:
https://www.aclweb.org/anthology/D19-5552
DOI:
10.18653/v1/D19-5552
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-5552.pdf