@inproceedings{schulz-etal-2012-resource,
title = "A Resource-light Approach to Phrase Extraction for {E}nglish and {G}erman Documents from the Patent Domain and User Generated Content",
author = "Schulz, Julia Maria and
Becks, Daniela and
Womser-Hacker, Christa and
Mandl, Thomas",
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/466_Paper.pdf",
pages = "538--543",
abstract = "In order to extract meaningful phrases from corpora (e. g. in an information retrieval context) intensive knowledge of the domain in question and the respective documents is generally needed. When moving to a new domain or language the underlying knowledge bases and models need to be adapted, which is often time-consuming and labor-intensive. This paper adresses the described challenge of phrase extraction from documents in different domains and languages and proposes an approach, which does not use comprehensive lexica and therefore can be easily transferred to new domains and languages. The effectiveness of the proposed approach is evaluated on user generated content and documents from the patent domain in English and German.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schulz-etal-2012-resource">
<titleInfo>
<title>A Resource-light Approach to Phrase Extraction for English and German Documents from the Patent Domain and User Generated Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Schulz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Becks</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christa</namePart>
<namePart type="family">Womser-Hacker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Mandl</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>In order to extract meaningful phrases from corpora (e. g. in an information retrieval context) intensive knowledge of the domain in question and the respective documents is generally needed. When moving to a new domain or language the underlying knowledge bases and models need to be adapted, which is often time-consuming and labor-intensive. This paper adresses the described challenge of phrase extraction from documents in different domains and languages and proposes an approach, which does not use comprehensive lexica and therefore can be easily transferred to new domains and languages. The effectiveness of the proposed approach is evaluated on user generated content and documents from the patent domain in English and German.</abstract>
<identifier type="citekey">schulz-etal-2012-resource</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/466_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>538</start>
<end>543</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Resource-light Approach to Phrase Extraction for English and German Documents from the Patent Domain and User Generated Content
%A Schulz, Julia Maria
%A Becks, Daniela
%A Womser-Hacker, Christa
%A Mandl, Thomas
%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 schulz-etal-2012-resource
%X In order to extract meaningful phrases from corpora (e. g. in an information retrieval context) intensive knowledge of the domain in question and the respective documents is generally needed. When moving to a new domain or language the underlying knowledge bases and models need to be adapted, which is often time-consuming and labor-intensive. This paper adresses the described challenge of phrase extraction from documents in different domains and languages and proposes an approach, which does not use comprehensive lexica and therefore can be easily transferred to new domains and languages. The effectiveness of the proposed approach is evaluated on user generated content and documents from the patent domain in English and German.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/466_Paper.pdf
%P 538-543
Markdown (Informal)
[A Resource-light Approach to Phrase Extraction for English and German Documents from the Patent Domain and User Generated Content](http://www.lrec-conf.org/proceedings/lrec2012/pdf/466_Paper.pdf) (Schulz et al., LREC 2012)
ACL