@inproceedings{sindlerova-bojar-2010-building,
title = "Building a Bilingual {V}al{L}ex Using Treebank Token Alignment: First Observations",
author = "{\v{S}}indlerov{\'a}, Jana and
Bojar, Ond{\v{r}}ej",
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/568_Paper.pdf",
abstract = "We explore the potential and limitations of a concept of building a bilingual valency lexicon based on the alignment of nodes in a parallel treebank. Our aim is to build an electronic Czech-{\textgreater}English Valency Lexicon by collecting equivalences from bilingual treebank data and storing them in two already existing electronic valency lexicons, PDT-VALLEX and Engvallex. For this task a special annotation interface has been built upon the TrEd editor, allowing quick and easy collecting of frame equivalences in either of the source lexicons. The issues encountered so far include limitations of technical character, theory-dependent limitations and limitations concerning the achievable degree of quality of human annotation. The issues of special interest for both linguists and MT specialists involved in the project include linguistically motivated non-balance between the frame equivalents, either in number or in type of valency participants. The first phases of annotation so far attest the assumption that there is a unique correspondence between the functors of the translation-equivalent frames. Also, hardly any linguistically significant non-balance between the frames has been found, which is partly promising considering the linguistic theory used and partly caused by little stylistic variety of the annotated corpus texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sindlerova-bojar-2010-building">
<titleInfo>
<title>Building a Bilingual ValLex Using Treebank Token Alignment: First Observations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Šindlerová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</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>We explore the potential and limitations of a concept of building a bilingual valency lexicon based on the alignment of nodes in a parallel treebank. Our aim is to build an electronic Czech-\textgreaterEnglish Valency Lexicon by collecting equivalences from bilingual treebank data and storing them in two already existing electronic valency lexicons, PDT-VALLEX and Engvallex. For this task a special annotation interface has been built upon the TrEd editor, allowing quick and easy collecting of frame equivalences in either of the source lexicons. The issues encountered so far include limitations of technical character, theory-dependent limitations and limitations concerning the achievable degree of quality of human annotation. The issues of special interest for both linguists and MT specialists involved in the project include linguistically motivated non-balance between the frame equivalents, either in number or in type of valency participants. The first phases of annotation so far attest the assumption that there is a unique correspondence between the functors of the translation-equivalent frames. Also, hardly any linguistically significant non-balance between the frames has been found, which is partly promising considering the linguistic theory used and partly caused by little stylistic variety of the annotated corpus texts.</abstract>
<identifier type="citekey">sindlerova-bojar-2010-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/568_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Bilingual ValLex Using Treebank Token Alignment: First Observations
%A Šindlerová, Jana
%A Bojar, Ondřej
%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 sindlerova-bojar-2010-building
%X We explore the potential and limitations of a concept of building a bilingual valency lexicon based on the alignment of nodes in a parallel treebank. Our aim is to build an electronic Czech-\textgreaterEnglish Valency Lexicon by collecting equivalences from bilingual treebank data and storing them in two already existing electronic valency lexicons, PDT-VALLEX and Engvallex. For this task a special annotation interface has been built upon the TrEd editor, allowing quick and easy collecting of frame equivalences in either of the source lexicons. The issues encountered so far include limitations of technical character, theory-dependent limitations and limitations concerning the achievable degree of quality of human annotation. The issues of special interest for both linguists and MT specialists involved in the project include linguistically motivated non-balance between the frame equivalents, either in number or in type of valency participants. The first phases of annotation so far attest the assumption that there is a unique correspondence between the functors of the translation-equivalent frames. Also, hardly any linguistically significant non-balance between the frames has been found, which is partly promising considering the linguistic theory used and partly caused by little stylistic variety of the annotated corpus texts.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/568_Paper.pdf
Markdown (Informal)
[Building a Bilingual ValLex Using Treebank Token Alignment: First Observations](http://www.lrec-conf.org/proceedings/lrec2010/pdf/568_Paper.pdf) (Šindlerová & Bojar, LREC 2010)
ACL