@inproceedings{sporleder-etal-2006-identifying,
title = "Identifying Named Entities in Text Databases from the Natural History Domain",
author = "Sporleder, Caroline and
van Erp, Marieke and
Porcelijn, Tijn and
van den Bosch, Antal and
Arntzen, Pim",
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/482_pdf.pdf",
abstract = "In this paper, we investigate whether it is possible to bootstrap a named entity tagger for textual databases by exploiting the database structure to automatically generate domain and database-specific gazetteer lists. We compare three tagging strategies: (i) using the extracted gazetteers in a look-up tagger, (ii) using the gazetteers to automatically extract training data to train a database-specific tagger, and (iii) using a generic named entity tagger. Our results suggest that automatically built gazetteers in combination with a look-up tagger lead to a relatively good performance and that generic taggers do not perform particularly well on this type of data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sporleder-etal-2006-identifying">
<titleInfo>
<title>Identifying Named Entities in Text Databases from the Natural History Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Caroline</namePart>
<namePart type="family">Sporleder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marieke</namePart>
<namePart type="family">van Erp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tijn</namePart>
<namePart type="family">Porcelijn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antal</namePart>
<namePart type="family">van den Bosch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pim</namePart>
<namePart type="family">Arntzen</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>In this paper, we investigate whether it is possible to bootstrap a named entity tagger for textual databases by exploiting the database structure to automatically generate domain and database-specific gazetteer lists. We compare three tagging strategies: (i) using the extracted gazetteers in a look-up tagger, (ii) using the gazetteers to automatically extract training data to train a database-specific tagger, and (iii) using a generic named entity tagger. Our results suggest that automatically built gazetteers in combination with a look-up tagger lead to a relatively good performance and that generic taggers do not perform particularly well on this type of data.</abstract>
<identifier type="citekey">sporleder-etal-2006-identifying</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/482_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Named Entities in Text Databases from the Natural History Domain
%A Sporleder, Caroline
%A van Erp, Marieke
%A Porcelijn, Tijn
%A van den Bosch, Antal
%A Arntzen, Pim
%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 sporleder-etal-2006-identifying
%X In this paper, we investigate whether it is possible to bootstrap a named entity tagger for textual databases by exploiting the database structure to automatically generate domain and database-specific gazetteer lists. We compare three tagging strategies: (i) using the extracted gazetteers in a look-up tagger, (ii) using the gazetteers to automatically extract training data to train a database-specific tagger, and (iii) using a generic named entity tagger. Our results suggest that automatically built gazetteers in combination with a look-up tagger lead to a relatively good performance and that generic taggers do not perform particularly well on this type of data.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/482_pdf.pdf
Markdown (Informal)
[Identifying Named Entities in Text Databases from the Natural History Domain](http://www.lrec-conf.org/proceedings/lrec2006/pdf/482_pdf.pdf) (Sporleder et al., LREC 2006)
ACL