@inproceedings{kliegr-zamazal-2014-towards,
title = "Towards Linked Hypernyms Dataset 2.0: complementing {DB}pedia with hypernym discovery",
author = "Kliegr, Tom{\'a}{\v{s}} and
Zamazal, Ond{\v{r}}ej",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/703_Paper.pdf",
pages = "3517--3523",
abstract = "This paper presents a statistical type inference algorithm for ontology alignment, which assigns DBpedia entities with a new type (class). To infer types for a specific entity, the algorithm first identifies types that co-occur with the type the entity already has, and subsequently prunes the set of candidates for the most confident one. The algorithm has one parameter for balancing specificity/reliability of the resulting type selection. The proposed algorithm is used to complement the types in the LHD dataset, which is RDF knowledge base populated by identifying hypernyms from the free text of Wikipedia articles. The majority of types assigned to entities in LHD 1.0 are DBpedia resources. Through the statistical type inference, the number of entities with a type from DBpedia Ontology is increased significantly: by 750 thousand entities for the English dataset, 200.000 for Dutch and 440.000 for German. The accuracy of the inferred types is at 0.65 for English (as compared to 0.86 for LHD 1.0 types). A byproduct of the mapping process is a set of 11.000 mappings from DBpedia resources to DBpedia Ontology classes with associated confidence values. The number of the resulting mappings is an order of magnitude larger than what can be achieved with standard ontology alignment algorithms (Falcon, LogMapLt and YAM++), which do not utilize the type co-occurrence information. The presented algorithm is not restricted to the LHD dataset, it can be used to address generic type inference problems in presence of class membership information for a large number of instances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kliegr-zamazal-2014-towards">
<titleInfo>
<title>Towards Linked Hypernyms Dataset 2.0: complementing DBpedia with hypernym discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Kliegr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Zamazal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a statistical type inference algorithm for ontology alignment, which assigns DBpedia entities with a new type (class). To infer types for a specific entity, the algorithm first identifies types that co-occur with the type the entity already has, and subsequently prunes the set of candidates for the most confident one. The algorithm has one parameter for balancing specificity/reliability of the resulting type selection. The proposed algorithm is used to complement the types in the LHD dataset, which is RDF knowledge base populated by identifying hypernyms from the free text of Wikipedia articles. The majority of types assigned to entities in LHD 1.0 are DBpedia resources. Through the statistical type inference, the number of entities with a type from DBpedia Ontology is increased significantly: by 750 thousand entities for the English dataset, 200.000 for Dutch and 440.000 for German. The accuracy of the inferred types is at 0.65 for English (as compared to 0.86 for LHD 1.0 types). A byproduct of the mapping process is a set of 11.000 mappings from DBpedia resources to DBpedia Ontology classes with associated confidence values. The number of the resulting mappings is an order of magnitude larger than what can be achieved with standard ontology alignment algorithms (Falcon, LogMapLt and YAM++), which do not utilize the type co-occurrence information. The presented algorithm is not restricted to the LHD dataset, it can be used to address generic type inference problems in presence of class membership information for a large number of instances.</abstract>
<identifier type="citekey">kliegr-zamazal-2014-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/703_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3517</start>
<end>3523</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Linked Hypernyms Dataset 2.0: complementing DBpedia with hypernym discovery
%A Kliegr, Tomáš
%A Zamazal, Ondřej
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F kliegr-zamazal-2014-towards
%X This paper presents a statistical type inference algorithm for ontology alignment, which assigns DBpedia entities with a new type (class). To infer types for a specific entity, the algorithm first identifies types that co-occur with the type the entity already has, and subsequently prunes the set of candidates for the most confident one. The algorithm has one parameter for balancing specificity/reliability of the resulting type selection. The proposed algorithm is used to complement the types in the LHD dataset, which is RDF knowledge base populated by identifying hypernyms from the free text of Wikipedia articles. The majority of types assigned to entities in LHD 1.0 are DBpedia resources. Through the statistical type inference, the number of entities with a type from DBpedia Ontology is increased significantly: by 750 thousand entities for the English dataset, 200.000 for Dutch and 440.000 for German. The accuracy of the inferred types is at 0.65 for English (as compared to 0.86 for LHD 1.0 types). A byproduct of the mapping process is a set of 11.000 mappings from DBpedia resources to DBpedia Ontology classes with associated confidence values. The number of the resulting mappings is an order of magnitude larger than what can be achieved with standard ontology alignment algorithms (Falcon, LogMapLt and YAM++), which do not utilize the type co-occurrence information. The presented algorithm is not restricted to the LHD dataset, it can be used to address generic type inference problems in presence of class membership information for a large number of instances.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/703_Paper.pdf
%P 3517-3523
Markdown (Informal)
[Towards Linked Hypernyms Dataset 2.0: complementing DBpedia with hypernym discovery](http://www.lrec-conf.org/proceedings/lrec2014/pdf/703_Paper.pdf) (Kliegr & Zamazal, LREC 2014)
ACL