@inproceedings{yamamoto-etal-2008-extraction,
title = "Extraction of Informative Expressions from Domain-specific Documents",
author = "Yamamoto, Eiko and
Isahara, Hitoshi and
Terada, Akira and
Abe, Yasunori",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/410_paper.pdf",
abstract = "What kinds of lexical resources are helpful for extracting useful information from domain-specific documents? Although domain-specific documents contain much useful knowledge, it is not obvious how to extract such knowledge efficiently from the documents. We need to develop techniques for extracting hidden information from such domain-specific documents. These techniques do not necessarily use state-of-the-art technologies and achieve deep and accurate language understanding, but are based on huge amounts of linguistic resources, such as domain-specific lexical databases. In this paper, we introduce two techniques for extracting informative expressions from documents: the extraction of related words that are not only taxonomically related but also thematically related, and the acquisition of salient terms and phrases. With these techniques we then attempt to automatically and statistically extract domain-specific informative expressions in aviation documents as an example and evaluate the results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yamamoto-etal-2008-extraction">
<titleInfo>
<title>Extraction of Informative Expressions from Domain-specific Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eiko</namePart>
<namePart type="family">Yamamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akira</namePart>
<namePart type="family">Terada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasunori</namePart>
<namePart type="family">Abe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>What kinds of lexical resources are helpful for extracting useful information from domain-specific documents? Although domain-specific documents contain much useful knowledge, it is not obvious how to extract such knowledge efficiently from the documents. We need to develop techniques for extracting hidden information from such domain-specific documents. These techniques do not necessarily use state-of-the-art technologies and achieve deep and accurate language understanding, but are based on huge amounts of linguistic resources, such as domain-specific lexical databases. In this paper, we introduce two techniques for extracting informative expressions from documents: the extraction of related words that are not only taxonomically related but also thematically related, and the acquisition of salient terms and phrases. With these techniques we then attempt to automatically and statistically extract domain-specific informative expressions in aviation documents as an example and evaluate the results.</abstract>
<identifier type="citekey">yamamoto-etal-2008-extraction</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/410_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extraction of Informative Expressions from Domain-specific Documents
%A Yamamoto, Eiko
%A Isahara, Hitoshi
%A Terada, Akira
%A Abe, Yasunori
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F yamamoto-etal-2008-extraction
%X What kinds of lexical resources are helpful for extracting useful information from domain-specific documents? Although domain-specific documents contain much useful knowledge, it is not obvious how to extract such knowledge efficiently from the documents. We need to develop techniques for extracting hidden information from such domain-specific documents. These techniques do not necessarily use state-of-the-art technologies and achieve deep and accurate language understanding, but are based on huge amounts of linguistic resources, such as domain-specific lexical databases. In this paper, we introduce two techniques for extracting informative expressions from documents: the extraction of related words that are not only taxonomically related but also thematically related, and the acquisition of salient terms and phrases. With these techniques we then attempt to automatically and statistically extract domain-specific informative expressions in aviation documents as an example and evaluate the results.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/410_paper.pdf
Markdown (Informal)
[Extraction of Informative Expressions from Domain-specific Documents](http://www.lrec-conf.org/proceedings/lrec2008/pdf/410_paper.pdf) (Yamamoto et al., LREC 2008)
ACL