@inproceedings{escudero-etal-2014-use,
title = "On the use of a fuzzy classifier to speed up the {S}p{\_}{T}o{BI} labeling of the Glissando {S}panish corpus",
author = "Escudero, David and
Aguilar-Cuevas, Lourdes and
Gonz{\'a}lez-Ferreras, C{\'e}sar and
Guti{\'e}rrez-Gonz{\'a}lez, Yurena and
Carde{\~n}oso-Payo, Valent{\'\i}n",
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/1066_Paper.pdf",
pages = "1962--1969",
abstract = "In this paper, we present the application of a novel automatic prosodic labeling methodology for speeding up the manual labeling of the Glissando corpus (Spanish read news items). The methodology is based on the use of soft classification techniques. The output of the automatic system consists on a set of label candidates per word. The number of predicted candidates depends on the degree of certainty assigned by the classifier to each of the predictions. The manual transcriber checks the sets of predictions to select the correct one. We describe the fundamentals of the fuzzy classification tool and its training with a corpus labeled with Sp TOBI labels. Results show a clear coherence between the most confused labels in the output of the automatic classifier and the most confused labels detected in inter-transcriber consistency tests. More importantly, in a preliminary test, the real time ratio of the labeling process was 1:66 when the template of predictions is used and 1:80 when it is not.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="escudero-etal-2014-use">
<titleInfo>
<title>On the use of a fuzzy classifier to speed up the Sp_ToBI labeling of the Glissando Spanish corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Escudero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lourdes</namePart>
<namePart type="family">Aguilar-Cuevas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">César</namePart>
<namePart type="family">González-Ferreras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yurena</namePart>
<namePart type="family">Gutiérrez-González</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentín</namePart>
<namePart type="family">Cardeñoso-Payo</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>In this paper, we present the application of a novel automatic prosodic labeling methodology for speeding up the manual labeling of the Glissando corpus (Spanish read news items). The methodology is based on the use of soft classification techniques. The output of the automatic system consists on a set of label candidates per word. The number of predicted candidates depends on the degree of certainty assigned by the classifier to each of the predictions. The manual transcriber checks the sets of predictions to select the correct one. We describe the fundamentals of the fuzzy classification tool and its training with a corpus labeled with Sp TOBI labels. Results show a clear coherence between the most confused labels in the output of the automatic classifier and the most confused labels detected in inter-transcriber consistency tests. More importantly, in a preliminary test, the real time ratio of the labeling process was 1:66 when the template of predictions is used and 1:80 when it is not.</abstract>
<identifier type="citekey">escudero-etal-2014-use</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1066_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1962</start>
<end>1969</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the use of a fuzzy classifier to speed up the Sp_ToBI labeling of the Glissando Spanish corpus
%A Escudero, David
%A Aguilar-Cuevas, Lourdes
%A González-Ferreras, César
%A Gutiérrez-González, Yurena
%A Cardeñoso-Payo, Valentín
%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 escudero-etal-2014-use
%X In this paper, we present the application of a novel automatic prosodic labeling methodology for speeding up the manual labeling of the Glissando corpus (Spanish read news items). The methodology is based on the use of soft classification techniques. The output of the automatic system consists on a set of label candidates per word. The number of predicted candidates depends on the degree of certainty assigned by the classifier to each of the predictions. The manual transcriber checks the sets of predictions to select the correct one. We describe the fundamentals of the fuzzy classification tool and its training with a corpus labeled with Sp TOBI labels. Results show a clear coherence between the most confused labels in the output of the automatic classifier and the most confused labels detected in inter-transcriber consistency tests. More importantly, in a preliminary test, the real time ratio of the labeling process was 1:66 when the template of predictions is used and 1:80 when it is not.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1066_Paper.pdf
%P 1962-1969
Markdown (Informal)
[On the use of a fuzzy classifier to speed up the Sp_ToBI labeling of the Glissando Spanish corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1066_Paper.pdf) (Escudero et al., LREC 2014)
ACL