@inproceedings{degaetano-ortlieb-etal-2014-data,
title = "Data Mining with Shallow vs. Linguistic Features to Study Diversification of Scientific Registers",
author = "Degaetano-Ortlieb, Stefania and
Fankhauser, Peter and
Kermes, Hannah and
Lapshinova-Koltunski, Ekaterina and
Ordan, Noam and
Teich, Elke",
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/291_Paper.pdf",
pages = "1327--1334",
abstract = "We present a methodology to analyze the linguistic evolution of scientific registers with data mining techniques, comparing the insights gained from shallow vs. linguistic features. The focus is on selected scientific disciplines at the boundaries to computer science (computational linguistics, bioinformatics, digital construction, microelectronics). The data basis is the English Scientific Text Corpus (SCITEX) which covers a time range of roughly thirty years (1970/80s to early 2000s) (Degaetano-Ortlieb et al., 2013; Teich and Fankhauser, 2010). In particular, we investigate the diversification of scientific registers over time. Our theoretical basis is Systemic Functional Linguistics (SFL) and its specific incarnation of register theory (Halliday and Hasan, 1985). In terms of methods, we combine corpus-based methods of feature extraction and data mining techniques.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="degaetano-ortlieb-etal-2014-data">
<titleInfo>
<title>Data Mining with Shallow vs. Linguistic Features to Study Diversification of Scientific Registers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Fankhauser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Kermes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Lapshinova-Koltunski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noam</namePart>
<namePart type="family">Ordan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elke</namePart>
<namePart type="family">Teich</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>We present a methodology to analyze the linguistic evolution of scientific registers with data mining techniques, comparing the insights gained from shallow vs. linguistic features. The focus is on selected scientific disciplines at the boundaries to computer science (computational linguistics, bioinformatics, digital construction, microelectronics). The data basis is the English Scientific Text Corpus (SCITEX) which covers a time range of roughly thirty years (1970/80s to early 2000s) (Degaetano-Ortlieb et al., 2013; Teich and Fankhauser, 2010). In particular, we investigate the diversification of scientific registers over time. Our theoretical basis is Systemic Functional Linguistics (SFL) and its specific incarnation of register theory (Halliday and Hasan, 1985). In terms of methods, we combine corpus-based methods of feature extraction and data mining techniques.</abstract>
<identifier type="citekey">degaetano-ortlieb-etal-2014-data</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/291_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1327</start>
<end>1334</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Mining with Shallow vs. Linguistic Features to Study Diversification of Scientific Registers
%A Degaetano-Ortlieb, Stefania
%A Fankhauser, Peter
%A Kermes, Hannah
%A Lapshinova-Koltunski, Ekaterina
%A Ordan, Noam
%A Teich, Elke
%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 degaetano-ortlieb-etal-2014-data
%X We present a methodology to analyze the linguistic evolution of scientific registers with data mining techniques, comparing the insights gained from shallow vs. linguistic features. The focus is on selected scientific disciplines at the boundaries to computer science (computational linguistics, bioinformatics, digital construction, microelectronics). The data basis is the English Scientific Text Corpus (SCITEX) which covers a time range of roughly thirty years (1970/80s to early 2000s) (Degaetano-Ortlieb et al., 2013; Teich and Fankhauser, 2010). In particular, we investigate the diversification of scientific registers over time. Our theoretical basis is Systemic Functional Linguistics (SFL) and its specific incarnation of register theory (Halliday and Hasan, 1985). In terms of methods, we combine corpus-based methods of feature extraction and data mining techniques.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/291_Paper.pdf
%P 1327-1334
Markdown (Informal)
[Data Mining with Shallow vs. Linguistic Features to Study Diversification of Scientific Registers](http://www.lrec-conf.org/proceedings/lrec2014/pdf/291_Paper.pdf) (Degaetano-Ortlieb et al., LREC 2014)
ACL