@inproceedings{semmar-etal-2006-deep,
title = "A Deep Linguistic Analysis for Cross-language Information Retrieval",
author = "Semmar, Nasredine and
Laib, Meriama and
Fluhr, Christian",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/308_pdf.pdf",
abstract = "Cross-language information retrieval consists in providing a query in one language and searching documents in one or different languages. These documents are ordered by the probability of being relevant to the user's request. The highest ranked document is considered to be the most likely relevant document. The LIC2M cross-language information retrieval system is a weighted Boolean search engine based on a deep linguistic analysis of the query and the documents. This system is composed of a linguistic analyzer, a statistic analyzer, a reformulator, a comparator and a search engine. The linguistic analysis processes both documents to be indexed and queries to extract concepts representing their content. This analysis includes a morphological analysis, a part-of-speech tagging and a syntactic analysis. In this paper, we present the deep linguistic analysis used in the LIC2M cross-lingual search engine and we will particularly focus on the impact of the syntactic analysis on the retrieval effectiveness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="semmar-etal-2006-deep">
<titleInfo>
<title>A Deep Linguistic Analysis for Cross-language Information Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nasredine</namePart>
<namePart type="family">Semmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meriama</namePart>
<namePart type="family">Laib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Fluhr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-language information retrieval consists in providing a query in one language and searching documents in one or different languages. These documents are ordered by the probability of being relevant to the user’s request. The highest ranked document is considered to be the most likely relevant document. The LIC2M cross-language information retrieval system is a weighted Boolean search engine based on a deep linguistic analysis of the query and the documents. This system is composed of a linguistic analyzer, a statistic analyzer, a reformulator, a comparator and a search engine. The linguistic analysis processes both documents to be indexed and queries to extract concepts representing their content. This analysis includes a morphological analysis, a part-of-speech tagging and a syntactic analysis. In this paper, we present the deep linguistic analysis used in the LIC2M cross-lingual search engine and we will particularly focus on the impact of the syntactic analysis on the retrieval effectiveness.</abstract>
<identifier type="citekey">semmar-etal-2006-deep</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/308_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Deep Linguistic Analysis for Cross-language Information Retrieval
%A Semmar, Nasredine
%A Laib, Meriama
%A Fluhr, Christian
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F semmar-etal-2006-deep
%X Cross-language information retrieval consists in providing a query in one language and searching documents in one or different languages. These documents are ordered by the probability of being relevant to the user’s request. The highest ranked document is considered to be the most likely relevant document. The LIC2M cross-language information retrieval system is a weighted Boolean search engine based on a deep linguistic analysis of the query and the documents. This system is composed of a linguistic analyzer, a statistic analyzer, a reformulator, a comparator and a search engine. The linguistic analysis processes both documents to be indexed and queries to extract concepts representing their content. This analysis includes a morphological analysis, a part-of-speech tagging and a syntactic analysis. In this paper, we present the deep linguistic analysis used in the LIC2M cross-lingual search engine and we will particularly focus on the impact of the syntactic analysis on the retrieval effectiveness.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/308_pdf.pdf
Markdown (Informal)
[A Deep Linguistic Analysis for Cross-language Information Retrieval](http://www.lrec-conf.org/proceedings/lrec2006/pdf/308_pdf.pdf) (Semmar et al., LREC 2006)
ACL