SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment

<p dir="ltr">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 wordv...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Jisun An (10230800) (author)
مؤلفون آخرون: Haewoon Kwak (5747558) (author), Yong-Yeol Ahn (220468) (author)
منشور في: 2018
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513513035137024
author Jisun An (10230800)
author2 Haewoon Kwak (5747558)
Yong-Yeol Ahn (220468)
author2_role author
author
author_facet Jisun An (10230800)
Haewoon Kwak (5747558)
Yong-Yeol Ahn (220468)
author_role author
dc.creator.none.fl_str_mv Jisun An (10230800)
Haewoon Kwak (5747558)
Yong-Yeol Ahn (220468)
dc.date.none.fl_str_mv 2018-01-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.18653/v1/p18-1228
dc.relation.none.fl_str_mv https://figshare.com/articles/conference_contribution/SemAxis_A_Lightweight_Framework_to_Characterize_Domain-Specific_Word_Semantics_Beyond_Sentiment/25921075
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Language, communication and culture
Linguistics
Word semantics
Domain-specific
SEMAXIS
Semantic axes
Word vector spaces
Sentiment analysis
dc.title.none.fl_str_mv SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment
dc.type.none.fl_str_mv Text
Conference contribution
info:eu-repo/semantics/publishedVersion
text
conference object
description <p dir="ltr">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 wordvector 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-theart approaches in building domain-specific sentiment lexicons.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.18653/v1/p18-1228" target="_blank">https://dx.doi.org/10.18653/v1/p18-1228</a></p>
eu_rights_str_mv openAccess
id Manara2_15aeae69fc38b0959bbf630578234253
identifier_str_mv 10.18653/v1/p18-1228
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25921075
publishDate 2018
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond SentimentJisun An (10230800)Haewoon Kwak (5747558)Yong-Yeol Ahn (220468)Information and computing sciencesArtificial intelligenceLanguage, communication and cultureLinguisticsWord semanticsDomain-specificSEMAXISSemantic axesWord vector spacesSentiment analysis<p dir="ltr">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 wordvector 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-theart approaches in building domain-specific sentiment lexicons.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.18653/v1/p18-1228" target="_blank">https://dx.doi.org/10.18653/v1/p18-1228</a></p>2018-01-01T00:00:00ZTextConference contributioninfo:eu-repo/semantics/publishedVersiontextconference object10.18653/v1/p18-1228https://figshare.com/articles/conference_contribution/SemAxis_A_Lightweight_Framework_to_Characterize_Domain-Specific_Word_Semantics_Beyond_Sentiment/25921075CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/259210752018-01-01T00:00:00Z
spellingShingle SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment
Jisun An (10230800)
Information and computing sciences
Artificial intelligence
Language, communication and culture
Linguistics
Word semantics
Domain-specific
SEMAXIS
Semantic axes
Word vector spaces
Sentiment analysis
status_str publishedVersion
title SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment
title_full SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment
title_fullStr SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment
title_full_unstemmed SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment
title_short SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment
title_sort SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment
topic Information and computing sciences
Artificial intelligence
Language, communication and culture
Linguistics
Word semantics
Domain-specific
SEMAXIS
Semantic axes
Word vector spaces
Sentiment analysis