@inproceedings{abramowicz-etal-2006-linguistic,
title = "Linguistic Suite for {P}olish Cadastral System",
author = "Abramowicz, Witold and
Filipowska, Agata and
Piskorski, Jakub and
W{\k{e}}cel, Krzysztof and
Wieloch, Karol",
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/603_pdf.pdf",
abstract = "This paper reports on an endeavour of creating basic linguistic resources for geo-referencing of Polish free-text documents. We have defined a fine-grained named entity hierarchy, produced an exhaustive gazetteer, and developed named-entity grammars for Polish. Additionally, an annotated corpus for the cadastral domain was prepared for evaluation purposes. Our baseline approach to geo-referencing is based on application of aforementioned resources and a lightweight co-referencing technique which utilizes string-similarity metric of Jaro-Winkler. We carried out a detailed evaluation of detecting locations, organizations and persons, which revealed that best results are obtained via application of a combined grammar for all types. The application of lightweight co-referencing for organizations and persons improves recall but deteriorates precision, and no gain is observed for locations. The paper is accompanied by a demo, a geo-referencing application capable of: (a) finding documents and text fragments based on named entities and (b) populating the spatial ontology from texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abramowicz-etal-2006-linguistic">
<titleInfo>
<title>Linguistic Suite for Polish Cadastral System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Witold</namePart>
<namePart type="family">Abramowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Filipowska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krzysztof</namePart>
<namePart type="family">Węcel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karol</namePart>
<namePart type="family">Wieloch</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>This paper reports on an endeavour of creating basic linguistic resources for geo-referencing of Polish free-text documents. We have defined a fine-grained named entity hierarchy, produced an exhaustive gazetteer, and developed named-entity grammars for Polish. Additionally, an annotated corpus for the cadastral domain was prepared for evaluation purposes. Our baseline approach to geo-referencing is based on application of aforementioned resources and a lightweight co-referencing technique which utilizes string-similarity metric of Jaro-Winkler. We carried out a detailed evaluation of detecting locations, organizations and persons, which revealed that best results are obtained via application of a combined grammar for all types. The application of lightweight co-referencing for organizations and persons improves recall but deteriorates precision, and no gain is observed for locations. The paper is accompanied by a demo, a geo-referencing application capable of: (a) finding documents and text fragments based on named entities and (b) populating the spatial ontology from texts.</abstract>
<identifier type="citekey">abramowicz-etal-2006-linguistic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/603_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistic Suite for Polish Cadastral System
%A Abramowicz, Witold
%A Filipowska, Agata
%A Piskorski, Jakub
%A Węcel, Krzysztof
%A Wieloch, Karol
%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 abramowicz-etal-2006-linguistic
%X This paper reports on an endeavour of creating basic linguistic resources for geo-referencing of Polish free-text documents. We have defined a fine-grained named entity hierarchy, produced an exhaustive gazetteer, and developed named-entity grammars for Polish. Additionally, an annotated corpus for the cadastral domain was prepared for evaluation purposes. Our baseline approach to geo-referencing is based on application of aforementioned resources and a lightweight co-referencing technique which utilizes string-similarity metric of Jaro-Winkler. We carried out a detailed evaluation of detecting locations, organizations and persons, which revealed that best results are obtained via application of a combined grammar for all types. The application of lightweight co-referencing for organizations and persons improves recall but deteriorates precision, and no gain is observed for locations. The paper is accompanied by a demo, a geo-referencing application capable of: (a) finding documents and text fragments based on named entities and (b) populating the spatial ontology from texts.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/603_pdf.pdf
Markdown (Informal)
[Linguistic Suite for Polish Cadastral System](http://www.lrec-conf.org/proceedings/lrec2006/pdf/603_pdf.pdf) (Abramowicz et al., LREC 2006)
ACL
- Witold Abramowicz, Agata Filipowska, Jakub Piskorski, Krzysztof Węcel, and Karol Wieloch. 2006. Linguistic Suite for Polish Cadastral System. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).