@inproceedings{keleg-etal-2020-unsupervised,
title = "An Unsupervised Method for Weighting Finite-state Morphological Analyzers",
author = "Keleg, Amr and
Tyers, Francis and
Howell, Nick and
Pirinen, Tommi",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.474",
pages = "3842--3850",
abstract = "Morphological analysis is one of the tasks that have been studied for years. Different techniques have been used to develop models for performing morphological analysis. Models based on finite state transducers have proved to be more suitable for languages with low available resources. In this paper, we have developed a method for weighting a morphological analyzer built using finite state transducers in order to disambiguate its results. The method is based on a word2vec model that is trained in a completely unsupervised way using raw untagged corpora and is able to capture the semantic meaning of the words. Most of the methods used for disambiguating the results of a morphological analyzer relied on having tagged corpora that need to manually built. Additionally, the method developed uses information about the token irrespective of its context unlike most of the other techniques that heavily rely on the word{'}s context to disambiguate its set of candidate analyses.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keleg-etal-2020-unsupervised">
<titleInfo>
<title>An Unsupervised Method for Weighting Finite-state Morphological Analyzers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nick</namePart>
<namePart type="family">Howell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Morphological analysis is one of the tasks that have been studied for years. Different techniques have been used to develop models for performing morphological analysis. Models based on finite state transducers have proved to be more suitable for languages with low available resources. In this paper, we have developed a method for weighting a morphological analyzer built using finite state transducers in order to disambiguate its results. The method is based on a word2vec model that is trained in a completely unsupervised way using raw untagged corpora and is able to capture the semantic meaning of the words. Most of the methods used for disambiguating the results of a morphological analyzer relied on having tagged corpora that need to manually built. Additionally, the method developed uses information about the token irrespective of its context unlike most of the other techniques that heavily rely on the word’s context to disambiguate its set of candidate analyses.</abstract>
<identifier type="citekey">keleg-etal-2020-unsupervised</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.474</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3842</start>
<end>3850</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Unsupervised Method for Weighting Finite-state Morphological Analyzers
%A Keleg, Amr
%A Tyers, Francis
%A Howell, Nick
%A Pirinen, Tommi
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F keleg-etal-2020-unsupervised
%X Morphological analysis is one of the tasks that have been studied for years. Different techniques have been used to develop models for performing morphological analysis. Models based on finite state transducers have proved to be more suitable for languages with low available resources. In this paper, we have developed a method for weighting a morphological analyzer built using finite state transducers in order to disambiguate its results. The method is based on a word2vec model that is trained in a completely unsupervised way using raw untagged corpora and is able to capture the semantic meaning of the words. Most of the methods used for disambiguating the results of a morphological analyzer relied on having tagged corpora that need to manually built. Additionally, the method developed uses information about the token irrespective of its context unlike most of the other techniques that heavily rely on the word’s context to disambiguate its set of candidate analyses.
%U https://aclanthology.org/2020.lrec-1.474
%P 3842-3850
Markdown (Informal)
[An Unsupervised Method for Weighting Finite-state Morphological Analyzers](https://aclanthology.org/2020.lrec-1.474) (Keleg et al., LREC 2020)
ACL