@inproceedings{fadaee-etal-2017-learning,
title = "Learning Topic-Sensitive Word Representations",
author = "Fadaee, Marzieh and
Bisazza, Arianna and
Monz, Christof",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-2070",
doi = "10.18653/v1/P17-2070",
pages = "441--447",
abstract = "Distributed word representations are widely used for modeling words in NLP tasks. Most of the existing models generate one representation per word and do not consider different meanings of a word. We present two approaches to learn multiple topic-sensitive representations per word by using Hierarchical Dirichlet Process. We observe that by modeling topics and integrating topic distributions for each document we obtain representations that are able to distinguish between different meanings of a given word. Our models yield statistically significant improvements for the lexical substitution task indicating that commonly used single word representations, even when combined with contextual information, are insufficient for this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fadaee-etal-2017-learning">
<titleInfo>
<title>Learning Topic-Sensitive Word Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Fadaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</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 2: Short 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>Distributed word representations are widely used for modeling words in NLP tasks. Most of the existing models generate one representation per word and do not consider different meanings of a word. We present two approaches to learn multiple topic-sensitive representations per word by using Hierarchical Dirichlet Process. We observe that by modeling topics and integrating topic distributions for each document we obtain representations that are able to distinguish between different meanings of a given word. Our models yield statistically significant improvements for the lexical substitution task indicating that commonly used single word representations, even when combined with contextual information, are insufficient for this task.</abstract>
<identifier type="citekey">fadaee-etal-2017-learning</identifier>
<identifier type="doi">10.18653/v1/P17-2070</identifier>
<location>
<url>https://aclanthology.org/P17-2070</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>441</start>
<end>447</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Topic-Sensitive Word Representations
%A Fadaee, Marzieh
%A Bisazza, Arianna
%A Monz, Christof
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F fadaee-etal-2017-learning
%X Distributed word representations are widely used for modeling words in NLP tasks. Most of the existing models generate one representation per word and do not consider different meanings of a word. We present two approaches to learn multiple topic-sensitive representations per word by using Hierarchical Dirichlet Process. We observe that by modeling topics and integrating topic distributions for each document we obtain representations that are able to distinguish between different meanings of a given word. Our models yield statistically significant improvements for the lexical substitution task indicating that commonly used single word representations, even when combined with contextual information, are insufficient for this task.
%R 10.18653/v1/P17-2070
%U https://aclanthology.org/P17-2070
%U https://doi.org/10.18653/v1/P17-2070
%P 441-447
Markdown (Informal)
[Learning Topic-Sensitive Word Representations](https://aclanthology.org/P17-2070) (Fadaee et al., ACL 2017)
ACL
- Marzieh Fadaee, Arianna Bisazza, and Christof Monz. 2017. Learning Topic-Sensitive Word Representations. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 441–447, Vancouver, Canada. Association for Computational Linguistics.