@inproceedings{li-etal-2010-enriching,
title = "Enriching Word Alignment with Linguistic Tags",
author = "Li, Xuansong and
Ge, Niyu and
Grimes, Stephen and
Strassel, Stephanie M. and
Maeda, Kazuaki",
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/670_Paper.pdf",
abstract = "Incorporating linguistic knowledge into word alignment is becoming increasingly important for current approaches in statistical machine translation research. To improve automatic word alignment and ultimately machine translation quality, an annotation framework is jointly proposed by LDC (Linguistic Data Consortium) and IBM. The framework enriches word alignment corpora to capture contextual, syntactic and language-specific features by introducing linguistic tags to the alignment annotation. Two annotation schemes constitute the framework: alignment and tagging. The alignment scheme aims to identify minimum translation units and translation relations by using minimum-match and attachment annotation approaches. A set of word tags and alignment link tags are designed in the tagging scheme to describe these translation units and relations. The framework produces a solid ground-level alignment base upon which larger translation unit alignment can be automatically induced. To test the soundness of this work, evaluation is performed on a pilot annotation, resulting in inter- and intra- annotator agreement of above 90{\%}. To date LDC has produced manual word alignment and tagging on 32,823 Chinese-English sentences following this framework.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2010-enriching">
<titleInfo>
<title>Enriching Word Alignment with Linguistic Tags</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">Niyu</namePart>
<namePart type="family">Ge</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="given">M</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuaki</namePart>
<namePart type="family">Maeda</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>Incorporating linguistic knowledge into word alignment is becoming increasingly important for current approaches in statistical machine translation research. To improve automatic word alignment and ultimately machine translation quality, an annotation framework is jointly proposed by LDC (Linguistic Data Consortium) and IBM. The framework enriches word alignment corpora to capture contextual, syntactic and language-specific features by introducing linguistic tags to the alignment annotation. Two annotation schemes constitute the framework: alignment and tagging. The alignment scheme aims to identify minimum translation units and translation relations by using minimum-match and attachment annotation approaches. A set of word tags and alignment link tags are designed in the tagging scheme to describe these translation units and relations. The framework produces a solid ground-level alignment base upon which larger translation unit alignment can be automatically induced. To test the soundness of this work, evaluation is performed on a pilot annotation, resulting in inter- and intra- annotator agreement of above 90%. To date LDC has produced manual word alignment and tagging on 32,823 Chinese-English sentences following this framework.</abstract>
<identifier type="citekey">li-etal-2010-enriching</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/670_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enriching Word Alignment with Linguistic Tags
%A Li, Xuansong
%A Ge, Niyu
%A Grimes, Stephen
%A Strassel, Stephanie M.
%A Maeda, Kazuaki
%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 li-etal-2010-enriching
%X Incorporating linguistic knowledge into word alignment is becoming increasingly important for current approaches in statistical machine translation research. To improve automatic word alignment and ultimately machine translation quality, an annotation framework is jointly proposed by LDC (Linguistic Data Consortium) and IBM. The framework enriches word alignment corpora to capture contextual, syntactic and language-specific features by introducing linguistic tags to the alignment annotation. Two annotation schemes constitute the framework: alignment and tagging. The alignment scheme aims to identify minimum translation units and translation relations by using minimum-match and attachment annotation approaches. A set of word tags and alignment link tags are designed in the tagging scheme to describe these translation units and relations. The framework produces a solid ground-level alignment base upon which larger translation unit alignment can be automatically induced. To test the soundness of this work, evaluation is performed on a pilot annotation, resulting in inter- and intra- annotator agreement of above 90%. To date LDC has produced manual word alignment and tagging on 32,823 Chinese-English sentences following this framework.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/670_Paper.pdf
Markdown (Informal)
[Enriching Word Alignment with Linguistic Tags](http://www.lrec-conf.org/proceedings/lrec2010/pdf/670_Paper.pdf) (Li et al., LREC 2010)
ACL
- Xuansong Li, Niyu Ge, Stephen Grimes, Stephanie M. Strassel, and Kazuaki Maeda. 2010. Enriching Word Alignment with Linguistic Tags. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).