@inproceedings{racz-etal-2014-4fx,
title = "4{FX}: Light Verb Constructions in a Multilingual Parallel Corpus",
author = "R{\'a}cz, Anita and
Nagy T., Istv{\'a}n and
Vincze, Veronika",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/331_Paper.pdf",
pages = "710--715",
abstract = "In this paper, we describe 4FX, a quadrilingual (English-Spanish-German-Hungarian) parallel corpus annotated for light verb constructions. We present the annotation process, and report statistical data on the frequency of LVCs in each language. We also offer inter-annotator agreement rates and we highlight some interesting facts and tendencies on the basis of comparing multilingual data from the four corpora. According to the frequency of LVC categories and the calculated Kendalls coefficient for the four corpora, we found that Spanish and German are very similar to each other, Hungarian is also similar to both, but German differs from all these three. The qualitative and quantitative data analysis might prove useful in theoretical linguistic research for all the four languages. Moreover, the corpus will be an excellent testbed for the development and evaluation of machine learning based methods aiming at extracting or identifying light verb constructions in these four languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="racz-etal-2014-4fx">
<titleInfo>
<title>4FX: Light Verb Constructions in a Multilingual Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">Rácz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">István</namePart>
<namePart type="family">Nagy T.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Vincze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe 4FX, a quadrilingual (English-Spanish-German-Hungarian) parallel corpus annotated for light verb constructions. We present the annotation process, and report statistical data on the frequency of LVCs in each language. We also offer inter-annotator agreement rates and we highlight some interesting facts and tendencies on the basis of comparing multilingual data from the four corpora. According to the frequency of LVC categories and the calculated Kendalls coefficient for the four corpora, we found that Spanish and German are very similar to each other, Hungarian is also similar to both, but German differs from all these three. The qualitative and quantitative data analysis might prove useful in theoretical linguistic research for all the four languages. Moreover, the corpus will be an excellent testbed for the development and evaluation of machine learning based methods aiming at extracting or identifying light verb constructions in these four languages.</abstract>
<identifier type="citekey">racz-etal-2014-4fx</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/331_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>710</start>
<end>715</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 4FX: Light Verb Constructions in a Multilingual Parallel Corpus
%A Rácz, Anita
%A Nagy T., István
%A Vincze, Veronika
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F racz-etal-2014-4fx
%X In this paper, we describe 4FX, a quadrilingual (English-Spanish-German-Hungarian) parallel corpus annotated for light verb constructions. We present the annotation process, and report statistical data on the frequency of LVCs in each language. We also offer inter-annotator agreement rates and we highlight some interesting facts and tendencies on the basis of comparing multilingual data from the four corpora. According to the frequency of LVC categories and the calculated Kendalls coefficient for the four corpora, we found that Spanish and German are very similar to each other, Hungarian is also similar to both, but German differs from all these three. The qualitative and quantitative data analysis might prove useful in theoretical linguistic research for all the four languages. Moreover, the corpus will be an excellent testbed for the development and evaluation of machine learning based methods aiming at extracting or identifying light verb constructions in these four languages.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/331_Paper.pdf
%P 710-715
Markdown (Informal)
[4FX: Light Verb Constructions in a Multilingual Parallel Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/331_Paper.pdf) (Rácz et al., LREC 2014)
ACL