@inproceedings{sato-kaide-2010-person,
title = "A Person-Name Filter for Automatic Compilation of Bilingual Person-Name Lexicons",
author = "Sato, Satoshi and
Kaide, Sayoko",
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/343_Paper.pdf",
abstract = "This paper proposes a simple and fast person-name filter, which plays an important role in automatic compilation of a large bilingual person-name lexicon. This filter is based on pn{\_}score, which is the sum of two component scores, the score of the first name and that of the last name. Each score is calculated from two term sets: one is a dense set in which most of the members are person names; another is a baseline set that contains less person names. The pn{\_}score takes one of five values, {+2, +1, 0, -1, -2}, which correspond to strong positive, positive, undecidable, negative, and strong negative, respectively. This pn{\_}score can be easily extended to bilingual pn{\_}score that takes one of nine values, by summing scores of two languages. Experimental results show that our method works well for monolingual person names in English and Japanese; the F-score of each language is 0.929 and 0.939, respectively. The performance of the bilingual person-name filter is better; the F-score is 0.955.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sato-kaide-2010-person">
<titleInfo>
<title>A Person-Name Filter for Automatic Compilation of Bilingual Person-Name Lexicons</title>
</titleInfo>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sayoko</namePart>
<namePart type="family">Kaide</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 proposes a simple and fast person-name filter, which plays an important role in automatic compilation of a large bilingual person-name lexicon. This filter is based on pn_score, which is the sum of two component scores, the score of the first name and that of the last name. Each score is calculated from two term sets: one is a dense set in which most of the members are person names; another is a baseline set that contains less person names. The pn_score takes one of five values, +2, +1, 0, -1, -2, which correspond to strong positive, positive, undecidable, negative, and strong negative, respectively. This pn_score can be easily extended to bilingual pn_score that takes one of nine values, by summing scores of two languages. Experimental results show that our method works well for monolingual person names in English and Japanese; the F-score of each language is 0.929 and 0.939, respectively. The performance of the bilingual person-name filter is better; the F-score is 0.955.</abstract>
<identifier type="citekey">sato-kaide-2010-person</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/343_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Person-Name Filter for Automatic Compilation of Bilingual Person-Name Lexicons
%A Sato, Satoshi
%A Kaide, Sayoko
%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 sato-kaide-2010-person
%X This paper proposes a simple and fast person-name filter, which plays an important role in automatic compilation of a large bilingual person-name lexicon. This filter is based on pn_score, which is the sum of two component scores, the score of the first name and that of the last name. Each score is calculated from two term sets: one is a dense set in which most of the members are person names; another is a baseline set that contains less person names. The pn_score takes one of five values, +2, +1, 0, -1, -2, which correspond to strong positive, positive, undecidable, negative, and strong negative, respectively. This pn_score can be easily extended to bilingual pn_score that takes one of nine values, by summing scores of two languages. Experimental results show that our method works well for monolingual person names in English and Japanese; the F-score of each language is 0.929 and 0.939, respectively. The performance of the bilingual person-name filter is better; the F-score is 0.955.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/343_Paper.pdf
Markdown (Informal)
[A Person-Name Filter for Automatic Compilation of Bilingual Person-Name Lexicons](http://www.lrec-conf.org/proceedings/lrec2010/pdf/343_Paper.pdf) (Sato & Kaide, LREC 2010)
ACL