@inproceedings{zervanou-etal-2014-word,
title = "Word Semantic Similarity for Morphologically Rich Languages",
author = "Zervanou, Kalliopi and
Iosif, Elias and
Potamianos, Alexandros",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/973_Paper.pdf",
abstract = "In this work, we investigate the role of morphology on the performance of semantic similarity for morphologically rich languages, such as German and Greek. The challenge in processing languages with richer morphology than English, lies in reducing estimation error while addressing the semantic distortion introduced by a stemmer or a lemmatiser. For this purpose, we propose a methodology for selective stemming, based on a semantic distortion metric. The proposed algorithm is tested on the task of similarity estimation between words using two types of corpus-based similarity metrics: co-occurrence-based and context-based. The performance on morphologically rich languages is boosted by stemming with the context-based metric, unlike English, where the best results are obtained by the co-occurrence-based metric. A key finding is that the estimation error reduction is different when a word is used as a feature, rather than when it is used as a target word.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zervanou-etal-2014-word">
<titleInfo>
<title>Word Semantic Similarity for Morphologically Rich Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kalliopi</namePart>
<namePart type="family">Zervanou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elias</namePart>
<namePart type="family">Iosif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Potamianos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we investigate the role of morphology on the performance of semantic similarity for morphologically rich languages, such as German and Greek. The challenge in processing languages with richer morphology than English, lies in reducing estimation error while addressing the semantic distortion introduced by a stemmer or a lemmatiser. For this purpose, we propose a methodology for selective stemming, based on a semantic distortion metric. The proposed algorithm is tested on the task of similarity estimation between words using two types of corpus-based similarity metrics: co-occurrence-based and context-based. The performance on morphologically rich languages is boosted by stemming with the context-based metric, unlike English, where the best results are obtained by the co-occurrence-based metric. A key finding is that the estimation error reduction is different when a word is used as a feature, rather than when it is used as a target word.</abstract>
<identifier type="citekey">zervanou-etal-2014-word</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/973_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Semantic Similarity for Morphologically Rich Languages
%A Zervanou, Kalliopi
%A Iosif, Elias
%A Potamianos, Alexandros
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F zervanou-etal-2014-word
%X In this work, we investigate the role of morphology on the performance of semantic similarity for morphologically rich languages, such as German and Greek. The challenge in processing languages with richer morphology than English, lies in reducing estimation error while addressing the semantic distortion introduced by a stemmer or a lemmatiser. For this purpose, we propose a methodology for selective stemming, based on a semantic distortion metric. The proposed algorithm is tested on the task of similarity estimation between words using two types of corpus-based similarity metrics: co-occurrence-based and context-based. The performance on morphologically rich languages is boosted by stemming with the context-based metric, unlike English, where the best results are obtained by the co-occurrence-based metric. A key finding is that the estimation error reduction is different when a word is used as a feature, rather than when it is used as a target word.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/973_Paper.pdf
Markdown (Informal)
[Word Semantic Similarity for Morphologically Rich Languages](http://www.lrec-conf.org/proceedings/lrec2014/pdf/973_Paper.pdf) (Zervanou et al., LREC 2014)
ACL