Unsupervised Learning of Style-sensitive Word Vectors

Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi, Kentaro Inui


Abstract
This paper presents the first study aimed at capturing stylistic similarity between words in an unsupervised manner. We propose extending the continuous bag of words (CBOW) embedding model (Mikolov et al., 2013b) to learn style-sensitive word vectors using a wider context window under the assumption that the style of all the words in an utterance is consistent. In addition, we introduce a novel task to predict lexical stylistic similarity and to create a benchmark dataset for this task. Our experiment with this dataset supports our assumption and demonstrates that the proposed extensions contribute to the acquisition of style-sensitive word embeddings.
Anthology ID:
P18-2091
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
572–578
Language:
URL:
https://aclanthology.org/P18-2091
DOI:
10.18653/v1/P18-2091
Bibkey:
Cite (ACL):
Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi, and Kentaro Inui. 2018. Unsupervised Learning of Style-sensitive Word Vectors. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 572–578, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Learning of Style-sensitive Word Vectors (Akama et al., ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/P18-2091.pdf
Poster:
 P18-2091.Poster.pdf
Data
Japanese Word Similarity