@inproceedings{le-etal-2018-deep,
title = "A Deep Dive into Word Sense Disambiguation with {LSTM}",
author = "Le, Minh and
Postma, Marten and
Urbani, Jacopo and
Vossen, Piek",
editor = "Bender, Emily M. and
Derczynski, Leon and
Isabelle, Pierre",
booktitle = "Proceedings of the 27th International Conference on Computational Linguistics",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/C18-1030",
pages = "354--365",
abstract = "LSTM-based language models have been shown effective in Word Sense Disambiguation (WSD). In particular, the technique proposed by Yuan et al. (2016) returned state-of-the-art performance in several benchmarks, but neither the training data nor the source code was released. This paper presents the results of a reproduction study and analysis of this technique using only openly available datasets (GigaWord, SemCor, OMSTI) and software (TensorFlow). Our study showed that similar results can be obtained with much less data than hinted at by Yuan et al. (2016). Detailed analyses shed light on the strengths and weaknesses of this method. First, adding more unannotated training data is useful, but is subject to diminishing returns. Second, the model can correctly identify both popular and unpopular meanings. Finally, the limited sense coverage in the annotated datasets is a major limitation. All code and trained models are made freely available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-etal-2018-deep">
<titleInfo>
<title>A Deep Dive into Word Sense Disambiguation with LSTM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marten</namePart>
<namePart type="family">Postma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacopo</namePart>
<namePart type="family">Urbani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Bender</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Isabelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>LSTM-based language models have been shown effective in Word Sense Disambiguation (WSD). In particular, the technique proposed by Yuan et al. (2016) returned state-of-the-art performance in several benchmarks, but neither the training data nor the source code was released. This paper presents the results of a reproduction study and analysis of this technique using only openly available datasets (GigaWord, SemCor, OMSTI) and software (TensorFlow). Our study showed that similar results can be obtained with much less data than hinted at by Yuan et al. (2016). Detailed analyses shed light on the strengths and weaknesses of this method. First, adding more unannotated training data is useful, but is subject to diminishing returns. Second, the model can correctly identify both popular and unpopular meanings. Finally, the limited sense coverage in the annotated datasets is a major limitation. All code and trained models are made freely available.</abstract>
<identifier type="citekey">le-etal-2018-deep</identifier>
<location>
<url>https://aclanthology.org/C18-1030</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>354</start>
<end>365</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Deep Dive into Word Sense Disambiguation with LSTM
%A Le, Minh
%A Postma, Marten
%A Urbani, Jacopo
%A Vossen, Piek
%Y Bender, Emily M.
%Y Derczynski, Leon
%Y Isabelle, Pierre
%S Proceedings of the 27th International Conference on Computational Linguistics
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F le-etal-2018-deep
%X LSTM-based language models have been shown effective in Word Sense Disambiguation (WSD). In particular, the technique proposed by Yuan et al. (2016) returned state-of-the-art performance in several benchmarks, but neither the training data nor the source code was released. This paper presents the results of a reproduction study and analysis of this technique using only openly available datasets (GigaWord, SemCor, OMSTI) and software (TensorFlow). Our study showed that similar results can be obtained with much less data than hinted at by Yuan et al. (2016). Detailed analyses shed light on the strengths and weaknesses of this method. First, adding more unannotated training data is useful, but is subject to diminishing returns. Second, the model can correctly identify both popular and unpopular meanings. Finally, the limited sense coverage in the annotated datasets is a major limitation. All code and trained models are made freely available.
%U https://aclanthology.org/C18-1030
%P 354-365
Markdown (Informal)
[A Deep Dive into Word Sense Disambiguation with LSTM](https://aclanthology.org/C18-1030) (Le et al., COLING 2018)
ACL
- Minh Le, Marten Postma, Jacopo Urbani, and Piek Vossen. 2018. A Deep Dive into Word Sense Disambiguation with LSTM. In Proceedings of the 27th International Conference on Computational Linguistics, pages 354–365, Santa Fe, New Mexico, USA. Association for Computational Linguistics.