@inproceedings{sedoc-etal-2017-semantic,
title = "Semantic Word Clusters Using Signed Spectral Clustering",
author = "Sedoc, Jo{\~a}o and
Gallier, Jean and
Foster, Dean and
Ungar, Lyle",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1087",
doi = "10.18653/v1/P17-1087",
pages = "939--949",
abstract = "Vector space representations of words capture many aspects of word similarity, but such methods tend to produce vector spaces in which antonyms (as well as synonyms) are close to each other. For spectral clustering using such word embeddings, words are points in a vector space where synonyms are linked with positive weights, while antonyms are linked with negative weights. We present a new signed spectral normalized graph cut algorithm, \textit{signed clustering}, that overlays existing thesauri upon distributionally derived vector representations of words, so that antonym relationships between word pairs are represented by negative weights. Our signed clustering algorithm produces clusters of words that simultaneously capture distributional and synonym relations. By using randomized spectral decomposition (Halko et al., 2011) and sparse matrices, our method is both fast and scalable. We validate our clusters using datasets containing human judgments of word pair similarities and show the benefit of using our word clusters for sentiment prediction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sedoc-etal-2017-semantic">
<titleInfo>
<title>Semantic Word Clusters Using Signed Spectral Clustering</title>
</titleInfo>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean</namePart>
<namePart type="family">Gallier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dean</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyle</namePart>
<namePart type="family">Ungar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Vector space representations of words capture many aspects of word similarity, but such methods tend to produce vector spaces in which antonyms (as well as synonyms) are close to each other. For spectral clustering using such word embeddings, words are points in a vector space where synonyms are linked with positive weights, while antonyms are linked with negative weights. We present a new signed spectral normalized graph cut algorithm, signed clustering, that overlays existing thesauri upon distributionally derived vector representations of words, so that antonym relationships between word pairs are represented by negative weights. Our signed clustering algorithm produces clusters of words that simultaneously capture distributional and synonym relations. By using randomized spectral decomposition (Halko et al., 2011) and sparse matrices, our method is both fast and scalable. We validate our clusters using datasets containing human judgments of word pair similarities and show the benefit of using our word clusters for sentiment prediction.</abstract>
<identifier type="citekey">sedoc-etal-2017-semantic</identifier>
<identifier type="doi">10.18653/v1/P17-1087</identifier>
<location>
<url>https://aclanthology.org/P17-1087</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>939</start>
<end>949</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Word Clusters Using Signed Spectral Clustering
%A Sedoc, João
%A Gallier, Jean
%A Foster, Dean
%A Ungar, Lyle
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F sedoc-etal-2017-semantic
%X Vector space representations of words capture many aspects of word similarity, but such methods tend to produce vector spaces in which antonyms (as well as synonyms) are close to each other. For spectral clustering using such word embeddings, words are points in a vector space where synonyms are linked with positive weights, while antonyms are linked with negative weights. We present a new signed spectral normalized graph cut algorithm, signed clustering, that overlays existing thesauri upon distributionally derived vector representations of words, so that antonym relationships between word pairs are represented by negative weights. Our signed clustering algorithm produces clusters of words that simultaneously capture distributional and synonym relations. By using randomized spectral decomposition (Halko et al., 2011) and sparse matrices, our method is both fast and scalable. We validate our clusters using datasets containing human judgments of word pair similarities and show the benefit of using our word clusters for sentiment prediction.
%R 10.18653/v1/P17-1087
%U https://aclanthology.org/P17-1087
%U https://doi.org/10.18653/v1/P17-1087
%P 939-949
Markdown (Informal)
[Semantic Word Clusters Using Signed Spectral Clustering](https://aclanthology.org/P17-1087) (Sedoc et al., ACL 2017)
ACL
- João Sedoc, Jean Gallier, Dean Foster, and Lyle Ungar. 2017. Semantic Word Clusters Using Signed Spectral Clustering. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 939–949, Vancouver, Canada. Association for Computational Linguistics.