@inproceedings{chevelu-etal-2014-roots,
title = "{ROOTS}: a toolkit for easy, fast and consistent processing of large sequential annotated data collections",
author = "Chevelu, Jonathan and
Lecorv{\'e}, Gw{\'e}nol{\'e} and
Lolive, Damien",
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/338_Paper.pdf",
pages = "619--626",
abstract = "The development of new methods for given speech and natural language processing tasks usually consists in annotating large corpora of data before applying machine learning techniques to train models or to extract information. Beyond scientific aspects, creating and managing such annotated data sets is a recurrent problem. While using human annotators is obviously expensive in time and money, relying on automatic annotation processes is not a simple solution neither. Typically, the high diversity of annotation tools and of data formats, as well as the lack of efficient middleware to interface them all together, make such processes very complex and painful to design. To circumvent this problem, this paper presents the toolkit ROOTS, a freshly released open source toolkit (\url{http://roots-toolkit.gforge.inria.fr}) for easy, fast and consistent management of heterogeneously annotated data. ROOTS is designed to efficiently handle massive complex sequential data and to allow quick and light prototyping, as this is often required for research purposes. To illustrate these properties, three sample applications are presented in the field of speech and language processing, though ROOTS can more generally be easily extended to other application domains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chevelu-etal-2014-roots">
<titleInfo>
<title>ROOTS: a toolkit for easy, fast and consistent processing of large sequential annotated data collections</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Chevelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gwénolé</namePart>
<namePart type="family">Lecorvé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Lolive</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>The development of new methods for given speech and natural language processing tasks usually consists in annotating large corpora of data before applying machine learning techniques to train models or to extract information. Beyond scientific aspects, creating and managing such annotated data sets is a recurrent problem. While using human annotators is obviously expensive in time and money, relying on automatic annotation processes is not a simple solution neither. Typically, the high diversity of annotation tools and of data formats, as well as the lack of efficient middleware to interface them all together, make such processes very complex and painful to design. To circumvent this problem, this paper presents the toolkit ROOTS, a freshly released open source toolkit (http://roots-toolkit.gforge.inria.fr) for easy, fast and consistent management of heterogeneously annotated data. ROOTS is designed to efficiently handle massive complex sequential data and to allow quick and light prototyping, as this is often required for research purposes. To illustrate these properties, three sample applications are presented in the field of speech and language processing, though ROOTS can more generally be easily extended to other application domains.</abstract>
<identifier type="citekey">chevelu-etal-2014-roots</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/338_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>619</start>
<end>626</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ROOTS: a toolkit for easy, fast and consistent processing of large sequential annotated data collections
%A Chevelu, Jonathan
%A Lecorvé, Gwénolé
%A Lolive, Damien
%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 chevelu-etal-2014-roots
%X The development of new methods for given speech and natural language processing tasks usually consists in annotating large corpora of data before applying machine learning techniques to train models or to extract information. Beyond scientific aspects, creating and managing such annotated data sets is a recurrent problem. While using human annotators is obviously expensive in time and money, relying on automatic annotation processes is not a simple solution neither. Typically, the high diversity of annotation tools and of data formats, as well as the lack of efficient middleware to interface them all together, make such processes very complex and painful to design. To circumvent this problem, this paper presents the toolkit ROOTS, a freshly released open source toolkit (http://roots-toolkit.gforge.inria.fr) for easy, fast and consistent management of heterogeneously annotated data. ROOTS is designed to efficiently handle massive complex sequential data and to allow quick and light prototyping, as this is often required for research purposes. To illustrate these properties, three sample applications are presented in the field of speech and language processing, though ROOTS can more generally be easily extended to other application domains.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/338_Paper.pdf
%P 619-626
Markdown (Informal)
[ROOTS: a toolkit for easy, fast and consistent processing of large sequential annotated data collections](http://www.lrec-conf.org/proceedings/lrec2014/pdf/338_Paper.pdf) (Chevelu et al., LREC 2014)
ACL