@inproceedings{arehart-2010-indexing,
title = "Indexing Methods for Faster and More Effective Person Name Search",
author = "Arehart, Mark",
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/166_Paper.pdf",
abstract = "This paper compares several indexing methods for person names extracted from text, developed for an information retrieval system with requirements for fast approximate matching of noisy and multicultural Romanized names. Such matching algorithms are computationally expensive and unacceptably slow when used without an indexing or blocking step. The goal is to create a small candidate pool containing all the true matches that can be exhaustively searched by a more effective but slower name comparison method. In addition to dramatically faster search, some of the methods evaluated here led to modest gains in effectiveness by eliminating false positives. Four indexing techniques using either phonetic keys or substrings of name segments, with and without name segment stopword lists, were combined with three name matching algorithms. On a test set of 700 queries run against 70K noisy and multicultural names, the best-performing technique took just 2.1{\%} as long as a naive exhaustive search and increased F1 by 3 points, showing that an appropriate indexing technique can increase both speed and effectiveness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arehart-2010-indexing">
<titleInfo>
<title>Indexing Methods for Faster and More Effective Person Name Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Arehart</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>This paper compares several indexing methods for person names extracted from text, developed for an information retrieval system with requirements for fast approximate matching of noisy and multicultural Romanized names. Such matching algorithms are computationally expensive and unacceptably slow when used without an indexing or blocking step. The goal is to create a small candidate pool containing all the true matches that can be exhaustively searched by a more effective but slower name comparison method. In addition to dramatically faster search, some of the methods evaluated here led to modest gains in effectiveness by eliminating false positives. Four indexing techniques using either phonetic keys or substrings of name segments, with and without name segment stopword lists, were combined with three name matching algorithms. On a test set of 700 queries run against 70K noisy and multicultural names, the best-performing technique took just 2.1% as long as a naive exhaustive search and increased F1 by 3 points, showing that an appropriate indexing technique can increase both speed and effectiveness.</abstract>
<identifier type="citekey">arehart-2010-indexing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/166_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Indexing Methods for Faster and More Effective Person Name Search
%A Arehart, Mark
%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 arehart-2010-indexing
%X This paper compares several indexing methods for person names extracted from text, developed for an information retrieval system with requirements for fast approximate matching of noisy and multicultural Romanized names. Such matching algorithms are computationally expensive and unacceptably slow when used without an indexing or blocking step. The goal is to create a small candidate pool containing all the true matches that can be exhaustively searched by a more effective but slower name comparison method. In addition to dramatically faster search, some of the methods evaluated here led to modest gains in effectiveness by eliminating false positives. Four indexing techniques using either phonetic keys or substrings of name segments, with and without name segment stopword lists, were combined with three name matching algorithms. On a test set of 700 queries run against 70K noisy and multicultural names, the best-performing technique took just 2.1% as long as a naive exhaustive search and increased F1 by 3 points, showing that an appropriate indexing technique can increase both speed and effectiveness.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/166_Paper.pdf
Markdown (Informal)
[Indexing Methods for Faster and More Effective Person Name Search](http://www.lrec-conf.org/proceedings/lrec2010/pdf/166_Paper.pdf) (Arehart, LREC 2010)
ACL