Semaxis

A lightweight framework to characterize domain-specific word semantics beyond sentiment

Jisun An, Haewoon Kwak, Yong Yeol Ahn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Because word semantics can substantially change across communities and contexts, capturing domain-specific word semantics is an important challenge. Here, we propose SEMAXIS, a simple yet powerful framework to characterize word semantics using many semantic axes in word-vector spaces beyond sentiment. We demonstrate that SEMAXIS can capture nuanced semantic representations in multiple online communities. We also show that, when the sentiment axis is examined, SEMAXIS outperforms the state-of-the-art approaches in building domain-specific sentiment lexicons.

Original languageEnglish
Title of host publicationACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages2450-2461
Number of pages12
ISBN (Electronic)9781948087322
Publication statusPublished - 1 Jan 2018
Event56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia
Duration: 15 Jul 201820 Jul 2018

Publication series

NameACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume1

Conference

Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
CountryAustralia
CityMelbourne
Period15/7/1820/7/18

Fingerprint

Semantics
Vector spaces

ASJC Scopus subject areas

  • Software
  • Computational Theory and Mathematics

Cite this

An, J., Kwak, H., & Ahn, Y. Y. (2018). Semaxis: A lightweight framework to characterize domain-specific word semantics beyond sentiment. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (pp. 2450-2461). (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1). Association for Computational Linguistics (ACL).

Semaxis : A lightweight framework to characterize domain-specific word semantics beyond sentiment. / An, Jisun; Kwak, Haewoon; Ahn, Yong Yeol.

ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), 2018. p. 2450-2461 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

An, J, Kwak, H & Ahn, YY 2018, Semaxis: A lightweight framework to characterize domain-specific word semantics beyond sentiment. in ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 1, Association for Computational Linguistics (ACL), pp. 2450-2461, 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 15/7/18.
An J, Kwak H, Ahn YY. Semaxis: A lightweight framework to characterize domain-specific word semantics beyond sentiment. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL). 2018. p. 2450-2461. (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).
An, Jisun ; Kwak, Haewoon ; Ahn, Yong Yeol. / Semaxis : A lightweight framework to characterize domain-specific word semantics beyond sentiment. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), 2018. pp. 2450-2461 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).
@inproceedings{719e3044a455488aab29d4793510440a,
title = "Semaxis: A lightweight framework to characterize domain-specific word semantics beyond sentiment",
abstract = "Because word semantics can substantially change across communities and contexts, capturing domain-specific word semantics is an important challenge. Here, we propose SEMAXIS, a simple yet powerful framework to characterize word semantics using many semantic axes in word-vector spaces beyond sentiment. We demonstrate that SEMAXIS can capture nuanced semantic representations in multiple online communities. We also show that, when the sentiment axis is examined, SEMAXIS outperforms the state-of-the-art approaches in building domain-specific sentiment lexicons.",
author = "Jisun An and Haewoon Kwak and Ahn, {Yong Yeol}",
year = "2018",
month = "1",
day = "1",
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 = "2450--2461",
booktitle = "ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

}

TY - GEN

T1 - Semaxis

T2 - A lightweight framework to characterize domain-specific word semantics beyond sentiment

AU - An, Jisun

AU - Kwak, Haewoon

AU - Ahn, Yong Yeol

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Because word semantics can substantially change across communities and contexts, capturing domain-specific word semantics is an important challenge. Here, we propose SEMAXIS, a simple yet powerful framework to characterize word semantics using many semantic axes in word-vector spaces beyond sentiment. We demonstrate that SEMAXIS can capture nuanced semantic representations in multiple online communities. We also show that, when the sentiment axis is examined, SEMAXIS outperforms the state-of-the-art approaches in building domain-specific sentiment lexicons.

AB - Because word semantics can substantially change across communities and contexts, capturing domain-specific word semantics is an important challenge. Here, we propose SEMAXIS, a simple yet powerful framework to characterize word semantics using many semantic axes in word-vector spaces beyond sentiment. We demonstrate that SEMAXIS can capture nuanced semantic representations in multiple online communities. We also show that, when the sentiment axis is examined, SEMAXIS outperforms the state-of-the-art approaches in building domain-specific sentiment lexicons.

UR - http://www.scopus.com/inward/record.url?scp=85063104543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063104543&partnerID=8YFLogxK

M3 - Conference contribution

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

SP - 2450

EP - 2461

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

PB - Association for Computational Linguistics (ACL)

ER -