@inproceedings{mariani-etal-2014-facing,
title = "Facing the Identification Problem in Language-Related Scientific Data Analysis.",
author = "Mariani, Joseph and
Cieri, Christopher and
Francopoulo, Gil and
Paroubek, Patrick and
Delaborde, Marine",
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/945_Paper.pdf",
abstract = "This paper describes the problems that must be addressed when studying large amounts of data over time which require entity normalization applied not to the usual genres of news or political speech, but to the genre of academic discourse about language resources, technologies and sciences. It reports on the normalization processes that had to be applied to produce data usable for computing statistics in three past studies on the LRE Map, the ISCA Archive and the LDC Bibliography. It shows the need for human expertise during normalization and the necessity to adapt the work to the study objectives. It investigates possible improvements for reducing the workload necessary to produce comparable results. Through this paper, we show the necessity to define and agree on international persistent and unique identifiers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mariani-etal-2014-facing">
<titleInfo>
<title>Facing the Identification Problem in Language-Related Scientific Data Analysis.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gil</namePart>
<namePart type="family">Francopoulo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Paroubek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Delaborde</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 describes the problems that must be addressed when studying large amounts of data over time which require entity normalization applied not to the usual genres of news or political speech, but to the genre of academic discourse about language resources, technologies and sciences. It reports on the normalization processes that had to be applied to produce data usable for computing statistics in three past studies on the LRE Map, the ISCA Archive and the LDC Bibliography. It shows the need for human expertise during normalization and the necessity to adapt the work to the study objectives. It investigates possible improvements for reducing the workload necessary to produce comparable results. Through this paper, we show the necessity to define and agree on international persistent and unique identifiers.</abstract>
<identifier type="citekey">mariani-etal-2014-facing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/945_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Facing the Identification Problem in Language-Related Scientific Data Analysis.
%A Mariani, Joseph
%A Cieri, Christopher
%A Francopoulo, Gil
%A Paroubek, Patrick
%A Delaborde, Marine
%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 mariani-etal-2014-facing
%X This paper describes the problems that must be addressed when studying large amounts of data over time which require entity normalization applied not to the usual genres of news or political speech, but to the genre of academic discourse about language resources, technologies and sciences. It reports on the normalization processes that had to be applied to produce data usable for computing statistics in three past studies on the LRE Map, the ISCA Archive and the LDC Bibliography. It shows the need for human expertise during normalization and the necessity to adapt the work to the study objectives. It investigates possible improvements for reducing the workload necessary to produce comparable results. Through this paper, we show the necessity to define and agree on international persistent and unique identifiers.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/945_Paper.pdf
Markdown (Informal)
[Facing the Identification Problem in Language-Related Scientific Data Analysis.](http://www.lrec-conf.org/proceedings/lrec2014/pdf/945_Paper.pdf) (Mariani et al., LREC 2014)
ACL