@inproceedings{fishel-kirik-2010-linguistically,
title = "Linguistically Motivated Unsupervised Segmentation for Machine Translation",
author = "Fishel, Mark and
Kirik, Harri",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/604_Paper.pdf",
abstract = "In this paper we use statistical machine translation and morphology information from two different morphological analyzers to try to improve translation quality by linguistically motivated segmentation. The morphological analyzers we use are the unsupervised Morfessor morpheme segmentation and analyzer toolkit and the rule-based morphological analyzer T3. Our translations are done using the Moses statistical machine translation toolkit with training on the JRC-Acquis corpora and translating on Estonian to English and English to Estonian language directions. In our work we model such linguistic phenomena as word lemmas and endings and splitting compound words into simpler parts. Also lemma information was used to introduce new factors to the corpora and to use this information for better word alignment or for alternative path back-off translation. From the results we find that even though these methods have shown previously and keep showing promise of improved translation, their success still largely depends on the corpora and language pairs used.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fishel-kirik-2010-linguistically">
<titleInfo>
<title>Linguistically Motivated Unsupervised Segmentation for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harri</namePart>
<namePart type="family">Kirik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we use statistical machine translation and morphology information from two different morphological analyzers to try to improve translation quality by linguistically motivated segmentation. The morphological analyzers we use are the unsupervised Morfessor morpheme segmentation and analyzer toolkit and the rule-based morphological analyzer T3. Our translations are done using the Moses statistical machine translation toolkit with training on the JRC-Acquis corpora and translating on Estonian to English and English to Estonian language directions. In our work we model such linguistic phenomena as word lemmas and endings and splitting compound words into simpler parts. Also lemma information was used to introduce new factors to the corpora and to use this information for better word alignment or for alternative path back-off translation. From the results we find that even though these methods have shown previously and keep showing promise of improved translation, their success still largely depends on the corpora and language pairs used.</abstract>
<identifier type="citekey">fishel-kirik-2010-linguistically</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/604_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistically Motivated Unsupervised Segmentation for Machine Translation
%A Fishel, Mark
%A Kirik, Harri
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F fishel-kirik-2010-linguistically
%X In this paper we use statistical machine translation and morphology information from two different morphological analyzers to try to improve translation quality by linguistically motivated segmentation. The morphological analyzers we use are the unsupervised Morfessor morpheme segmentation and analyzer toolkit and the rule-based morphological analyzer T3. Our translations are done using the Moses statistical machine translation toolkit with training on the JRC-Acquis corpora and translating on Estonian to English and English to Estonian language directions. In our work we model such linguistic phenomena as word lemmas and endings and splitting compound words into simpler parts. Also lemma information was used to introduce new factors to the corpora and to use this information for better word alignment or for alternative path back-off translation. From the results we find that even though these methods have shown previously and keep showing promise of improved translation, their success still largely depends on the corpora and language pairs used.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/604_Paper.pdf
Markdown (Informal)
[Linguistically Motivated Unsupervised Segmentation for Machine Translation](http://www.lrec-conf.org/proceedings/lrec2010/pdf/604_Paper.pdf) (Fishel & Kirik, LREC 2010)
ACL