@inproceedings{kageback-salomonsson-2016-word,
title = "Word Sense Disambiguation using a Bidirectional {LSTM}",
author = {K{\aa}geb{\"a}ck, Mikael and
Salomonsson, Hans},
editor = "Zock, Michael and
Lenci, Alessandro and
Evert, Stefan",
booktitle = "Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon ({C}og{AL}ex - V)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-5307",
pages = "51--56",
abstract = "In this paper we present a clean, yet effective, model for word sense disambiguation. Our approach leverage a bidirectional long short-term memory network which is shared between all words. This enables the model to share statistical strength and to scale well with vocabulary size. The model is trained end-to-end, directly from the raw text to sense labels, and makes effective use of word order. We evaluate our approach on two standard datasets, using identical hyperparameter settings, which are in turn tuned on a third set of held out data. We employ no external resources (e.g. knowledge graphs, part-of-speech tagging, etc), language specific features, or hand crafted rules, but still achieve statistically equivalent results to the best state-of-the-art systems, that employ no such limitations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kageback-salomonsson-2016-word">
<titleInfo>
<title>Word Sense Disambiguation using a Bidirectional LSTM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikael</namePart>
<namePart type="family">Kågebäck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hans</namePart>
<namePart type="family">Salomonsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Zock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Evert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present a clean, yet effective, model for word sense disambiguation. Our approach leverage a bidirectional long short-term memory network which is shared between all words. This enables the model to share statistical strength and to scale well with vocabulary size. The model is trained end-to-end, directly from the raw text to sense labels, and makes effective use of word order. We evaluate our approach on two standard datasets, using identical hyperparameter settings, which are in turn tuned on a third set of held out data. We employ no external resources (e.g. knowledge graphs, part-of-speech tagging, etc), language specific features, or hand crafted rules, but still achieve statistically equivalent results to the best state-of-the-art systems, that employ no such limitations.</abstract>
<identifier type="citekey">kageback-salomonsson-2016-word</identifier>
<location>
<url>https://aclanthology.org/W16-5307</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>51</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Sense Disambiguation using a Bidirectional LSTM
%A Kågebäck, Mikael
%A Salomonsson, Hans
%Y Zock, Michael
%Y Lenci, Alessandro
%Y Evert, Stefan
%S Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F kageback-salomonsson-2016-word
%X In this paper we present a clean, yet effective, model for word sense disambiguation. Our approach leverage a bidirectional long short-term memory network which is shared between all words. This enables the model to share statistical strength and to scale well with vocabulary size. The model is trained end-to-end, directly from the raw text to sense labels, and makes effective use of word order. We evaluate our approach on two standard datasets, using identical hyperparameter settings, which are in turn tuned on a third set of held out data. We employ no external resources (e.g. knowledge graphs, part-of-speech tagging, etc), language specific features, or hand crafted rules, but still achieve statistically equivalent results to the best state-of-the-art systems, that employ no such limitations.
%U https://aclanthology.org/W16-5307
%P 51-56
Markdown (Informal)
[Word Sense Disambiguation using a Bidirectional LSTM](https://aclanthology.org/W16-5307) (Kågebäck & Salomonsson, CogALex 2016)
ACL