@inproceedings{black-etal-2014-evaluating,
title = "Evaluating Lemmatization Models for Machine-Assisted Corpus-Dictionary Linkage",
author = "Black, Kevin and
Ringger, Eric and
Felt, Paul and
Seppi, Kevin and
Heal, Kristian and
Lonsdale, Deryle",
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/1203_Paper.pdf",
pages = "3798--3805",
abstract = "The task of corpus-dictionary linkage (CDL) is to annotate each word in a corpus with a link to an appropriate dictionary entry that documents the sense and usage of the word. Corpus-dictionary linked resources include concordances, dictionaries with word usage examples, and corpora annotated with lemmas or word-senses. Such CDL resources are essential in learning a language and in linguistic research, translation, and philology. Lemmatization is a common approximation to automating corpus-dictionary linkage, where lemmas are treated as dictionary entry headwords. We intend to use data-driven lemmatization models to provide machine assistance to human annotators in the form of pre-annotations, and thereby reduce the costs of CDL annotation. In this work we adapt the discriminative string transducer DirecTL+ to perform lemmatization for classical Syriac, a low-resource language. We compare the accuracy of DirecTL+ with the Morfette discriminative lemmatizer. DirecTL+ achieves 96.92{\%} overall accuracy but only by a margin of 0.86{\%} over Morfette at the cost of a longer time to train the model. Error analysis on the models provides guidance on how to apply these models in a machine assistance setting for corpus-dictionary linkage.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="black-etal-2014-evaluating">
<titleInfo>
<title>Evaluating Lemmatization Models for Machine-Assisted Corpus-Dictionary Linkage</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Black</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Ringger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Felt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Seppi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristian</namePart>
<namePart type="family">Heal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deryle</namePart>
<namePart type="family">Lonsdale</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>The task of corpus-dictionary linkage (CDL) is to annotate each word in a corpus with a link to an appropriate dictionary entry that documents the sense and usage of the word. Corpus-dictionary linked resources include concordances, dictionaries with word usage examples, and corpora annotated with lemmas or word-senses. Such CDL resources are essential in learning a language and in linguistic research, translation, and philology. Lemmatization is a common approximation to automating corpus-dictionary linkage, where lemmas are treated as dictionary entry headwords. We intend to use data-driven lemmatization models to provide machine assistance to human annotators in the form of pre-annotations, and thereby reduce the costs of CDL annotation. In this work we adapt the discriminative string transducer DirecTL+ to perform lemmatization for classical Syriac, a low-resource language. We compare the accuracy of DirecTL+ with the Morfette discriminative lemmatizer. DirecTL+ achieves 96.92% overall accuracy but only by a margin of 0.86% over Morfette at the cost of a longer time to train the model. Error analysis on the models provides guidance on how to apply these models in a machine assistance setting for corpus-dictionary linkage.</abstract>
<identifier type="citekey">black-etal-2014-evaluating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1203_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3798</start>
<end>3805</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Lemmatization Models for Machine-Assisted Corpus-Dictionary Linkage
%A Black, Kevin
%A Ringger, Eric
%A Felt, Paul
%A Seppi, Kevin
%A Heal, Kristian
%A Lonsdale, Deryle
%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 black-etal-2014-evaluating
%X The task of corpus-dictionary linkage (CDL) is to annotate each word in a corpus with a link to an appropriate dictionary entry that documents the sense and usage of the word. Corpus-dictionary linked resources include concordances, dictionaries with word usage examples, and corpora annotated with lemmas or word-senses. Such CDL resources are essential in learning a language and in linguistic research, translation, and philology. Lemmatization is a common approximation to automating corpus-dictionary linkage, where lemmas are treated as dictionary entry headwords. We intend to use data-driven lemmatization models to provide machine assistance to human annotators in the form of pre-annotations, and thereby reduce the costs of CDL annotation. In this work we adapt the discriminative string transducer DirecTL+ to perform lemmatization for classical Syriac, a low-resource language. We compare the accuracy of DirecTL+ with the Morfette discriminative lemmatizer. DirecTL+ achieves 96.92% overall accuracy but only by a margin of 0.86% over Morfette at the cost of a longer time to train the model. Error analysis on the models provides guidance on how to apply these models in a machine assistance setting for corpus-dictionary linkage.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1203_Paper.pdf
%P 3798-3805
Markdown (Informal)
[Evaluating Lemmatization Models for Machine-Assisted Corpus-Dictionary Linkage](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1203_Paper.pdf) (Black et al., LREC 2014)
ACL