Unsupervised learning of style-sensitive word vectors

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

doi:10.18653/v1/p18-2091

Unsupervised learning of style-sensitive word vectors

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

INF - System Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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) model (Mikolov et al., 2013a) 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.

Original language	English
Title of host publication	ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
Publisher	Association for Computational Linguistics (ACL)
Pages	572-578
Number of pages	7
ISBN (Electronic)	9781948087346
DOIs	https://doi.org/10.18653/v1/p18-2091
Publication status	Published - 2018
Event	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia Duration: 2018 Jul 15 → 2018 Jul 20

Publication series

Name	ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume	2

Conference

Conference	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Country	Australia
City	Melbourne
Period	18/7/15 → 18/7/20

ASJC Scopus subject areas

Software
Computational Theory and Mathematics

Access to Document

10.18653/v1/p18-2091

Fingerprint Dive into the research topics of 'Unsupervised learning of style-sensitive word vectors'. Together they form a unique fingerprint.

Cite this

Akama, R., Watanabe, K., Yokoi, S., Kobayashi, S., & Inui, K. (2018). Unsupervised learning of style-sensitive word vectors. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers) (pp. 572-578). (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 2). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p18-2091

Unsupervised learning of style-sensitive word vectors. / Akama, Reina; Watanabe, Kento; Yokoi, Sho; Kobayashi, Sosuke; Inui, Kentaro.

ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL), 2018. p. 572-578 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Akama, R, Watanabe, K, Yokoi, S, Kobayashi, S & Inui, K 2018, Unsupervised learning of style-sensitive word vectors. in ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 2, Association for Computational Linguistics (ACL), pp. 572-578, 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 18/7/15. https://doi.org/10.18653/v1/p18-2091

Akama R, Watanabe K, Yokoi S, Kobayashi S, Inui K. Unsupervised learning of style-sensitive word vectors. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL). 2018. p. 572-578. (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)). https://doi.org/10.18653/v1/p18-2091

Akama, Reina ; Watanabe, Kento ; Yokoi, Sho ; Kobayashi, Sosuke ; Inui, Kentaro. / Unsupervised learning of style-sensitive word vectors. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL), 2018. pp. 572-578 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).

@inproceedings{33bbc70d8bb94287a537510588b7e288,

title = "Unsupervised learning of style-sensitive word vectors",

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) model (Mikolov et al., 2013a) 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.",

author = "Reina Akama and Kento Watanabe and Sho Yokoi and Sosuke Kobayashi and Kentaro Inui",

year = "2018",

doi = "10.18653/v1/p18-2091",

language = "English",

series = "ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

publisher = "Association for Computational Linguistics (ACL)",

pages = "572--578",

booktitle = "ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)",

note = "56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 ; Conference date: 15-07-2018 Through 20-07-2018",

}

TY - GEN

T1 - Unsupervised learning of style-sensitive word vectors

AU - Akama, Reina

AU - Watanabe, Kento

AU - Yokoi, Sho

AU - Kobayashi, Sosuke

AU - Inui, Kentaro

PY - 2018

Y1 - 2018

N2 - 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) model (Mikolov et al., 2013a) 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.

AB - 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) model (Mikolov et al., 2013a) 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.

UR - http://www.scopus.com/inward/record.url?scp=85063132000&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063132000&partnerID=8YFLogxK

U2 - 10.18653/v1/p18-2091

DO - 10.18653/v1/p18-2091

M3 - Conference contribution

AN - SCOPUS:85063132000

T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

SP - 572

EP - 578

BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)

PB - Association for Computational Linguistics (ACL)

T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018

Y2 - 15 July 2018 through 20 July 2018

ER -