@inproceedings{karlgren-etal-2008-experiments,
title = "Experiments to Investigate the Connection between Case Distribution and Topical Relevance of Search Terms in an Information Retrieval Setting",
author = "Karlgren, Jussi and
Dalianis, Hercules and
Jongejan, Bart",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/383_paper.pdf",
abstract = "We have performed a set of experiments made to investigate the utility of morphological analysis to improve retrieval of documents written in languages with relatively large morphological variation in a practical commercial setting, using the SiteSeeker search system developed and marketed by Euroling Ab. The objective of the experiments was to evaluate different lemmatisers and stemmers to determine which would be the most practical for the task at hand: highly interactive, relatively high precision web searches in commercial customer-oriented document collections. This paper gives an overview of some of the results for Finnish and German, and describes specifically one experiment designed to investigate the case distribution of nouns in a highly inflectional language (Finnish) and the topicality of the nouns in target texts. We find that topical nouns taken from queries are distributed differently over relevant and non-relevant documents depending on their grammatical case.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karlgren-etal-2008-experiments">
<titleInfo>
<title>Experiments to Investigate the Connection between Case Distribution and Topical Relevance of Search Terms in an Information Retrieval Setting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jussi</namePart>
<namePart type="family">Karlgren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hercules</namePart>
<namePart type="family">Dalianis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bart</namePart>
<namePart type="family">Jongejan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We have performed a set of experiments made to investigate the utility of morphological analysis to improve retrieval of documents written in languages with relatively large morphological variation in a practical commercial setting, using the SiteSeeker search system developed and marketed by Euroling Ab. The objective of the experiments was to evaluate different lemmatisers and stemmers to determine which would be the most practical for the task at hand: highly interactive, relatively high precision web searches in commercial customer-oriented document collections. This paper gives an overview of some of the results for Finnish and German, and describes specifically one experiment designed to investigate the case distribution of nouns in a highly inflectional language (Finnish) and the topicality of the nouns in target texts. We find that topical nouns taken from queries are distributed differently over relevant and non-relevant documents depending on their grammatical case.</abstract>
<identifier type="citekey">karlgren-etal-2008-experiments</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/383_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Experiments to Investigate the Connection between Case Distribution and Topical Relevance of Search Terms in an Information Retrieval Setting
%A Karlgren, Jussi
%A Dalianis, Hercules
%A Jongejan, Bart
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F karlgren-etal-2008-experiments
%X We have performed a set of experiments made to investigate the utility of morphological analysis to improve retrieval of documents written in languages with relatively large morphological variation in a practical commercial setting, using the SiteSeeker search system developed and marketed by Euroling Ab. The objective of the experiments was to evaluate different lemmatisers and stemmers to determine which would be the most practical for the task at hand: highly interactive, relatively high precision web searches in commercial customer-oriented document collections. This paper gives an overview of some of the results for Finnish and German, and describes specifically one experiment designed to investigate the case distribution of nouns in a highly inflectional language (Finnish) and the topicality of the nouns in target texts. We find that topical nouns taken from queries are distributed differently over relevant and non-relevant documents depending on their grammatical case.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/383_paper.pdf
Markdown (Informal)
[Experiments to Investigate the Connection between Case Distribution and Topical Relevance of Search Terms in an Information Retrieval Setting](http://www.lrec-conf.org/proceedings/lrec2008/pdf/383_paper.pdf) (Karlgren et al., LREC 2008)
ACL