@inproceedings{blessing-schutze-2010-fine,
title = "Fine-Grained Geographical Relation Extraction from {W}ikipedia",
author = {Blessing, Andre and
Sch{\"u}tze, Hinrich},
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/519_Paper.pdf",
abstract = "In this paper, we present work on enhancing the basic data resource of a context-aware system. Electronic text offers a wealth of information about geospatial data and can be used to improve the completeness and accuracy of geospatial resources (e.g., gazetteers). First, we introduce a supervised approach to extracting geographical relations on a fine-grained level. Second, we present a novel way of using Wikipedia as a corpus based on self-annotation. A self-annotation is an automatically created high-quality annotation that can be used for training and evaluation. Wikipedia contains two types of different context: (i) unstructured text and (ii) structured data: templates (e.g., infoboxes about cities), lists and tables. We use the structured data to annotate the unstructured text. Finally, the extracted fine-grained relations are used to complete gazetteer data. The precision and recall scores of more than 97 percent confirm that a statistical IE pipeline can be used to improve the data quality of community-based resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="blessing-schutze-2010-fine">
<titleInfo>
<title>Fine-Grained Geographical Relation Extraction from Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Blessing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schütze</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>In this paper, we present work on enhancing the basic data resource of a context-aware system. Electronic text offers a wealth of information about geospatial data and can be used to improve the completeness and accuracy of geospatial resources (e.g., gazetteers). First, we introduce a supervised approach to extracting geographical relations on a fine-grained level. Second, we present a novel way of using Wikipedia as a corpus based on self-annotation. A self-annotation is an automatically created high-quality annotation that can be used for training and evaluation. Wikipedia contains two types of different context: (i) unstructured text and (ii) structured data: templates (e.g., infoboxes about cities), lists and tables. We use the structured data to annotate the unstructured text. Finally, the extracted fine-grained relations are used to complete gazetteer data. The precision and recall scores of more than 97 percent confirm that a statistical IE pipeline can be used to improve the data quality of community-based resources.</abstract>
<identifier type="citekey">blessing-schutze-2010-fine</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/519_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Grained Geographical Relation Extraction from Wikipedia
%A Blessing, Andre
%A Schütze, Hinrich
%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 blessing-schutze-2010-fine
%X In this paper, we present work on enhancing the basic data resource of a context-aware system. Electronic text offers a wealth of information about geospatial data and can be used to improve the completeness and accuracy of geospatial resources (e.g., gazetteers). First, we introduce a supervised approach to extracting geographical relations on a fine-grained level. Second, we present a novel way of using Wikipedia as a corpus based on self-annotation. A self-annotation is an automatically created high-quality annotation that can be used for training and evaluation. Wikipedia contains two types of different context: (i) unstructured text and (ii) structured data: templates (e.g., infoboxes about cities), lists and tables. We use the structured data to annotate the unstructured text. Finally, the extracted fine-grained relations are used to complete gazetteer data. The precision and recall scores of more than 97 percent confirm that a statistical IE pipeline can be used to improve the data quality of community-based resources.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/519_Paper.pdf
Markdown (Informal)
[Fine-Grained Geographical Relation Extraction from Wikipedia](http://www.lrec-conf.org/proceedings/lrec2010/pdf/519_Paper.pdf) (Blessing & Schütze, LREC 2010)
ACL