@inproceedings{li-etal-2012-parallel,
title = "Parallel Aligned Treebanks at {LDC}: New Challenges Interfacing Existing Infrastructures",
author = "Li, Xuansong and
Strassel, Stephanie and
Grimes, Stephen and
Ismael, Safa and
Maamouri, Mohamed and
Bies, Ann and
Xue, Nianwen",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/277_Paper.pdf",
pages = "1848--1855",
abstract = "Parallel aligned treebanks (PAT) are linguistic corpora annotated with morphological and syntactic structures that are aligned at sentence as well as sub-sentence levels. They are valuable resources for improving machine translation (MT) quality. Recently, there has been an increasing demand for such data, especially for divergent language pairs. The Linguistic Data Consortium (LDC) and its academic partners have been developing Arabic-English and Chinese-English PATs for several years. This paper describes the PAT corpus creation effort for the program GALE (Global Autonomous Language Exploitation) and introduces the potential issues of scaling up this PAT effort for the program BOLT (Broad Operational Language Translation). Based on existing infrastructures and in the light of current annotation process, challenges and approaches, we are exploring new methodologies to address emerging challenges in constructing PATs, including data volume bottlenecks, dialect issues of Arabic languages, and new genre features related to rapidly changing social media. Preliminary experimental results are presented to show the feasibility of the approaches proposed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2012-parallel">
<titleInfo>
<title>Parallel Aligned Treebanks at LDC: New Challenges Interfacing Existing Infrastructures</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">Stephanie</namePart>
<namePart type="family">Strassel</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">Safa</namePart>
<namePart type="family">Ismael</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Maamouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Bies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parallel aligned treebanks (PAT) are linguistic corpora annotated with morphological and syntactic structures that are aligned at sentence as well as sub-sentence levels. They are valuable resources for improving machine translation (MT) quality. Recently, there has been an increasing demand for such data, especially for divergent language pairs. The Linguistic Data Consortium (LDC) and its academic partners have been developing Arabic-English and Chinese-English PATs for several years. This paper describes the PAT corpus creation effort for the program GALE (Global Autonomous Language Exploitation) and introduces the potential issues of scaling up this PAT effort for the program BOLT (Broad Operational Language Translation). Based on existing infrastructures and in the light of current annotation process, challenges and approaches, we are exploring new methodologies to address emerging challenges in constructing PATs, including data volume bottlenecks, dialect issues of Arabic languages, and new genre features related to rapidly changing social media. Preliminary experimental results are presented to show the feasibility of the approaches proposed.</abstract>
<identifier type="citekey">li-etal-2012-parallel</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/277_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1848</start>
<end>1855</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel Aligned Treebanks at LDC: New Challenges Interfacing Existing Infrastructures
%A Li, Xuansong
%A Strassel, Stephanie
%A Grimes, Stephen
%A Ismael, Safa
%A Maamouri, Mohamed
%A Bies, Ann
%A Xue, Nianwen
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F li-etal-2012-parallel
%X Parallel aligned treebanks (PAT) are linguistic corpora annotated with morphological and syntactic structures that are aligned at sentence as well as sub-sentence levels. They are valuable resources for improving machine translation (MT) quality. Recently, there has been an increasing demand for such data, especially for divergent language pairs. The Linguistic Data Consortium (LDC) and its academic partners have been developing Arabic-English and Chinese-English PATs for several years. This paper describes the PAT corpus creation effort for the program GALE (Global Autonomous Language Exploitation) and introduces the potential issues of scaling up this PAT effort for the program BOLT (Broad Operational Language Translation). Based on existing infrastructures and in the light of current annotation process, challenges and approaches, we are exploring new methodologies to address emerging challenges in constructing PATs, including data volume bottlenecks, dialect issues of Arabic languages, and new genre features related to rapidly changing social media. Preliminary experimental results are presented to show the feasibility of the approaches proposed.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/277_Paper.pdf
%P 1848-1855
Markdown (Informal)
[Parallel Aligned Treebanks at LDC: New Challenges Interfacing Existing Infrastructures](http://www.lrec-conf.org/proceedings/lrec2012/pdf/277_Paper.pdf) (Li et al., LREC 2012)
ACL