@article{wang-etal-2015-sense,
title = "A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment",
author = "Wang, Jing and
Bansal, Mohit and
Gimpel, Kevin and
Ziebart, Brian D. and
Yu, Clement T.",
editor = "Collins, Michael and
Lee, Lillian",
journal = "Transactions of the Association for Computational Linguistics",
volume = "3",
year = "2015",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q15-1005",
doi = "10.1162/tacl_a_00122",
pages = "59--71",
abstract = "Word sense induction (WSI) seeks to automatically discover the senses of a word in a corpus via unsupervised methods. We propose a sense-topic model for WSI, which treats sense and topic as two separate latent variables to be inferred jointly. Topics are informed by the entire document, while senses are informed by the local context surrounding the ambiguous word. We also discuss unsupervised ways of enriching the original corpus in order to improve model performance, including using neural word embeddings and external corpora to expand the context of each data instance. We demonstrate significant improvements over the previous state-of-the-art, achieving the best results reported to date on the SemEval-2013 WSI task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2015-sense">
<titleInfo>
<title>A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Gimpel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Ziebart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clement</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2015</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Word sense induction (WSI) seeks to automatically discover the senses of a word in a corpus via unsupervised methods. We propose a sense-topic model for WSI, which treats sense and topic as two separate latent variables to be inferred jointly. Topics are informed by the entire document, while senses are informed by the local context surrounding the ambiguous word. We also discuss unsupervised ways of enriching the original corpus in order to improve model performance, including using neural word embeddings and external corpora to expand the context of each data instance. We demonstrate significant improvements over the previous state-of-the-art, achieving the best results reported to date on the SemEval-2013 WSI task.</abstract>
<identifier type="citekey">wang-etal-2015-sense</identifier>
<identifier type="doi">10.1162/tacl_a_00122</identifier>
<location>
<url>https://aclanthology.org/Q15-1005</url>
</location>
<part>
<date>2015</date>
<detail type="volume"><number>3</number></detail>
<extent unit="page">
<start>59</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment
%A Wang, Jing
%A Bansal, Mohit
%A Gimpel, Kevin
%A Ziebart, Brian D.
%A Yu, Clement T.
%J Transactions of the Association for Computational Linguistics
%D 2015
%V 3
%I MIT Press
%C Cambridge, MA
%F wang-etal-2015-sense
%X Word sense induction (WSI) seeks to automatically discover the senses of a word in a corpus via unsupervised methods. We propose a sense-topic model for WSI, which treats sense and topic as two separate latent variables to be inferred jointly. Topics are informed by the entire document, while senses are informed by the local context surrounding the ambiguous word. We also discuss unsupervised ways of enriching the original corpus in order to improve model performance, including using neural word embeddings and external corpora to expand the context of each data instance. We demonstrate significant improvements over the previous state-of-the-art, achieving the best results reported to date on the SemEval-2013 WSI task.
%R 10.1162/tacl_a_00122
%U https://aclanthology.org/Q15-1005
%U https://doi.org/10.1162/tacl_a_00122
%P 59-71
Markdown (Informal)
[A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment](https://aclanthology.org/Q15-1005) (Wang et al., TACL 2015)
ACL