@inproceedings{li-etal-2016-uzbek,
title = "{U}zbek-{E}nglish and {T}urkish-{E}nglish Morpheme Alignment Corpora",
author = "Li, Xuansong and
Tracey, Jennifer and
Grimes, Stephen and
Strassel, Stephanie",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1467",
pages = "2925--2930",
abstract = "Morphologically-rich languages pose problems for machine translation (MT) systems, including word-alignment errors, data sparsity and multiple affixes. Current alignment models at word-level do not distinguish words and morphemes, thus yielding low-quality alignment and subsequently affecting end translation quality. Models using morpheme-level alignment can reduce the vocabulary size of morphologically-rich languages and overcomes data sparsity. The alignment data based on smallest units reveals subtle language features and enhances translation quality. Recent research proves such morpheme-level alignment (MA) data to be valuable linguistic resources for SMT, particularly for languages with rich morphology. In support of this research trend, the Linguistic Data Consortium (LDC) created Uzbek-English and Turkish-English alignment data which are manually aligned at the morpheme level. This paper describes the creation of MA corpora, including alignment and tagging process and approaches, highlighting annotation challenges and specific features of languages with rich morphology. The light tagging annotation on the alignment layer adds extra value to the MA data, facilitating users in flexibly tailoring the data for various MT model training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2016-uzbek">
<titleInfo>
<title>Uzbek-English and Turkish-English Morpheme Alignment Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuansong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Tracey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Grimes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Morphologically-rich languages pose problems for machine translation (MT) systems, including word-alignment errors, data sparsity and multiple affixes. Current alignment models at word-level do not distinguish words and morphemes, thus yielding low-quality alignment and subsequently affecting end translation quality. Models using morpheme-level alignment can reduce the vocabulary size of morphologically-rich languages and overcomes data sparsity. The alignment data based on smallest units reveals subtle language features and enhances translation quality. Recent research proves such morpheme-level alignment (MA) data to be valuable linguistic resources for SMT, particularly for languages with rich morphology. In support of this research trend, the Linguistic Data Consortium (LDC) created Uzbek-English and Turkish-English alignment data which are manually aligned at the morpheme level. This paper describes the creation of MA corpora, including alignment and tagging process and approaches, highlighting annotation challenges and specific features of languages with rich morphology. The light tagging annotation on the alignment layer adds extra value to the MA data, facilitating users in flexibly tailoring the data for various MT model training.</abstract>
<identifier type="citekey">li-etal-2016-uzbek</identifier>
<location>
<url>https://aclanthology.org/L16-1467</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2925</start>
<end>2930</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uzbek-English and Turkish-English Morpheme Alignment Corpora
%A Li, Xuansong
%A Tracey, Jennifer
%A Grimes, Stephen
%A Strassel, Stephanie
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F li-etal-2016-uzbek
%X Morphologically-rich languages pose problems for machine translation (MT) systems, including word-alignment errors, data sparsity and multiple affixes. Current alignment models at word-level do not distinguish words and morphemes, thus yielding low-quality alignment and subsequently affecting end translation quality. Models using morpheme-level alignment can reduce the vocabulary size of morphologically-rich languages and overcomes data sparsity. The alignment data based on smallest units reveals subtle language features and enhances translation quality. Recent research proves such morpheme-level alignment (MA) data to be valuable linguistic resources for SMT, particularly for languages with rich morphology. In support of this research trend, the Linguistic Data Consortium (LDC) created Uzbek-English and Turkish-English alignment data which are manually aligned at the morpheme level. This paper describes the creation of MA corpora, including alignment and tagging process and approaches, highlighting annotation challenges and specific features of languages with rich morphology. The light tagging annotation on the alignment layer adds extra value to the MA data, facilitating users in flexibly tailoring the data for various MT model training.
%U https://aclanthology.org/L16-1467
%P 2925-2930
Markdown (Informal)
[Uzbek-English and Turkish-English Morpheme Alignment Corpora](https://aclanthology.org/L16-1467) (Li et al., LREC 2016)
ACL
- Xuansong Li, Jennifer Tracey, Stephen Grimes, and Stephanie Strassel. 2016. Uzbek-English and Turkish-English Morpheme Alignment Corpora. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2925–2930, Portorož, Slovenia. European Language Resources Association (ELRA).