@inproceedings{damljanovic-etal-2012-applying,
title = "Applying Random Indexing to Structured Data to Find Contextually Similar Words",
author = "Damljanovi{\'c}, Danica and
Kruschwitz, Udo and
Albakour, M-Dyaa and
Petrak, Johann and
Lupu, Mihai",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/628_Paper.pdf",
pages = "2023--2030",
abstract = "Language resources extracted from structured data (e.g. Linked Open Data) have already been used in various scenarios to improve conventional Natural Language Processing techniques. The meanings of words and the relations between them are made more explicit in RDF graphs, in comparison to human-readable text, and hence have a great potential to improve legacy applications. In this paper, we describe an approach that can be used to extend or clarify the semantic meaning of a word by constructing a list of contextually related terms. Our approach is based on exploiting the structure inherent in an RDF graph and then applying the methods from statistical semantics, and in particular, Random Indexing, in order to discover contextually related terms. We evaluate our approach in the domain of life science using the dataset generated with the help of domain experts from a large pharmaceutical company (AstraZeneca). They were involved in two phases: firstly, to generate a set of keywords of interest to them, and secondly to judge the set of generated contextually similar words for each keyword of interest. We compare our proposed approach, exploiting the semantic graph, with the same method applied on the human readable text extracted from the graph.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="damljanovic-etal-2012-applying">
<titleInfo>
<title>Applying Random Indexing to Structured Data to Find Contextually Similar Words</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danica</namePart>
<namePart type="family">Damljanović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Kruschwitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M-Dyaa</namePart>
<namePart type="family">Albakour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johann</namePart>
<namePart type="family">Petrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Lupu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language resources extracted from structured data (e.g. Linked Open Data) have already been used in various scenarios to improve conventional Natural Language Processing techniques. The meanings of words and the relations between them are made more explicit in RDF graphs, in comparison to human-readable text, and hence have a great potential to improve legacy applications. In this paper, we describe an approach that can be used to extend or clarify the semantic meaning of a word by constructing a list of contextually related terms. Our approach is based on exploiting the structure inherent in an RDF graph and then applying the methods from statistical semantics, and in particular, Random Indexing, in order to discover contextually related terms. We evaluate our approach in the domain of life science using the dataset generated with the help of domain experts from a large pharmaceutical company (AstraZeneca). They were involved in two phases: firstly, to generate a set of keywords of interest to them, and secondly to judge the set of generated contextually similar words for each keyword of interest. We compare our proposed approach, exploiting the semantic graph, with the same method applied on the human readable text extracted from the graph.</abstract>
<identifier type="citekey">damljanovic-etal-2012-applying</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/628_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2023</start>
<end>2030</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Applying Random Indexing to Structured Data to Find Contextually Similar Words
%A Damljanović, Danica
%A Kruschwitz, Udo
%A Albakour, M-Dyaa
%A Petrak, Johann
%A Lupu, Mihai
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F damljanovic-etal-2012-applying
%X Language resources extracted from structured data (e.g. Linked Open Data) have already been used in various scenarios to improve conventional Natural Language Processing techniques. The meanings of words and the relations between them are made more explicit in RDF graphs, in comparison to human-readable text, and hence have a great potential to improve legacy applications. In this paper, we describe an approach that can be used to extend or clarify the semantic meaning of a word by constructing a list of contextually related terms. Our approach is based on exploiting the structure inherent in an RDF graph and then applying the methods from statistical semantics, and in particular, Random Indexing, in order to discover contextually related terms. We evaluate our approach in the domain of life science using the dataset generated with the help of domain experts from a large pharmaceutical company (AstraZeneca). They were involved in two phases: firstly, to generate a set of keywords of interest to them, and secondly to judge the set of generated contextually similar words for each keyword of interest. We compare our proposed approach, exploiting the semantic graph, with the same method applied on the human readable text extracted from the graph.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/628_Paper.pdf
%P 2023-2030
Markdown (Informal)
[Applying Random Indexing to Structured Data to Find Contextually Similar Words](http://www.lrec-conf.org/proceedings/lrec2012/pdf/628_Paper.pdf) (Damljanović et al., LREC 2012)
ACL