@inproceedings{wu-etal-2024-homophone2vec,
title = "{H}omophone2{V}ec: Embedding Space Analysis for Empirical Evaluation of Phonological and Semantic Similarity",
author = "Wu, Sophie and
Zheng, Anita and
Chuang, Joey",
editor = "Fu, Xiyan and
Fleisig, Eve",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-srw.34/",
doi = "10.18653/v1/2024.acl-srw.34",
pages = "287--292",
abstract = "This paper introduces a novel method for empirically evaluating the relationship between the phonological and semantic similarity of linguistic units using embedding spaces. Chinese character homophones are used as a proof-of-concept. We employ cosine similarity as a proxy for semantic similarity between characters, and compare relationships between phonologically-related characters and baseline characters (chosen as similar-frequency characters). We show there is a strongly statistically significant positive semantic relationship among different Chinese characters at varying levels of sound-sharing. We also perform some basic probing using t-SNE and UMAP visualizations, and indicate directions for future applications of this method."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-homophone2vec">
<titleInfo>
<title>Homophone2Vec: Embedding Space Analysis for Empirical Evaluation of Phonological and Semantic Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joey</namePart>
<namePart type="family">Chuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiyan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eve</namePart>
<namePart type="family">Fleisig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a novel method for empirically evaluating the relationship between the phonological and semantic similarity of linguistic units using embedding spaces. Chinese character homophones are used as a proof-of-concept. We employ cosine similarity as a proxy for semantic similarity between characters, and compare relationships between phonologically-related characters and baseline characters (chosen as similar-frequency characters). We show there is a strongly statistically significant positive semantic relationship among different Chinese characters at varying levels of sound-sharing. We also perform some basic probing using t-SNE and UMAP visualizations, and indicate directions for future applications of this method.</abstract>
<identifier type="citekey">wu-etal-2024-homophone2vec</identifier>
<identifier type="doi">10.18653/v1/2024.acl-srw.34</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-srw.34/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>287</start>
<end>292</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Homophone2Vec: Embedding Space Analysis for Empirical Evaluation of Phonological and Semantic Similarity
%A Wu, Sophie
%A Zheng, Anita
%A Chuang, Joey
%Y Fu, Xiyan
%Y Fleisig, Eve
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wu-etal-2024-homophone2vec
%X This paper introduces a novel method for empirically evaluating the relationship between the phonological and semantic similarity of linguistic units using embedding spaces. Chinese character homophones are used as a proof-of-concept. We employ cosine similarity as a proxy for semantic similarity between characters, and compare relationships between phonologically-related characters and baseline characters (chosen as similar-frequency characters). We show there is a strongly statistically significant positive semantic relationship among different Chinese characters at varying levels of sound-sharing. We also perform some basic probing using t-SNE and UMAP visualizations, and indicate directions for future applications of this method.
%R 10.18653/v1/2024.acl-srw.34
%U https://aclanthology.org/2024.luhme-srw.34/
%U https://doi.org/10.18653/v1/2024.acl-srw.34
%P 287-292
Markdown (Informal)
[Homophone2Vec: Embedding Space Analysis for Empirical Evaluation of Phonological and Semantic Similarity](https://aclanthology.org/2024.luhme-srw.34/) (Wu et al., ACL 2024)
ACL