@inproceedings{strakova-pecina-2010-czech,
title = "{C}zech Information Retrieval with Syntax-based Language Models",
author = "Strakov{\'a}, Jana and
Pecina, Pavel",
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/215_Paper.pdf",
abstract = "In recent years, considerable attention has been dedicated to language modeling methods in information retrieval. Although these approaches generally allow exploitation of any type of language model, most of the published experiments were conducted with a classical n-gram model, usually limited only to unigrams. A few works exploiting syntax in information retrieval can be cited in this context, but significant contribution of syntax based language modeling for information retrieval is yet to be proved. In this paper, we propose, implement, and evaluate an enrichment of language model employing syntactic dependency information acquired automatically from both documents and queries. Our experiments are conducted on Czech which is a morphologically rich language and has a considerably free word order, therefore a syntactic language model is expected to contribute positively to the unigram and bigram language model based on surface word order. By testing our model on the Czech test collection from Cross Language Evaluation Forum 2007 Ad-Hoc track, we show positive contribution of using dependency syntax in this context.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strakova-pecina-2010-czech">
<titleInfo>
<title>Czech Information Retrieval with Syntax-based Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Straková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Pecina</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>In recent years, considerable attention has been dedicated to language modeling methods in information retrieval. Although these approaches generally allow exploitation of any type of language model, most of the published experiments were conducted with a classical n-gram model, usually limited only to unigrams. A few works exploiting syntax in information retrieval can be cited in this context, but significant contribution of syntax based language modeling for information retrieval is yet to be proved. In this paper, we propose, implement, and evaluate an enrichment of language model employing syntactic dependency information acquired automatically from both documents and queries. Our experiments are conducted on Czech which is a morphologically rich language and has a considerably free word order, therefore a syntactic language model is expected to contribute positively to the unigram and bigram language model based on surface word order. By testing our model on the Czech test collection from Cross Language Evaluation Forum 2007 Ad-Hoc track, we show positive contribution of using dependency syntax in this context.</abstract>
<identifier type="citekey">strakova-pecina-2010-czech</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/215_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Czech Information Retrieval with Syntax-based Language Models
%A Straková, Jana
%A Pecina, Pavel
%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 strakova-pecina-2010-czech
%X In recent years, considerable attention has been dedicated to language modeling methods in information retrieval. Although these approaches generally allow exploitation of any type of language model, most of the published experiments were conducted with a classical n-gram model, usually limited only to unigrams. A few works exploiting syntax in information retrieval can be cited in this context, but significant contribution of syntax based language modeling for information retrieval is yet to be proved. In this paper, we propose, implement, and evaluate an enrichment of language model employing syntactic dependency information acquired automatically from both documents and queries. Our experiments are conducted on Czech which is a morphologically rich language and has a considerably free word order, therefore a syntactic language model is expected to contribute positively to the unigram and bigram language model based on surface word order. By testing our model on the Czech test collection from Cross Language Evaluation Forum 2007 Ad-Hoc track, we show positive contribution of using dependency syntax in this context.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/215_Paper.pdf
Markdown (Informal)
[Czech Information Retrieval with Syntax-based Language Models](http://www.lrec-conf.org/proceedings/lrec2010/pdf/215_Paper.pdf) (Straková & Pecina, LREC 2010)
ACL