@inproceedings{cabarrao-etal-2014-revising,
title = "Revising the annotation of a Broadcast News corpus: a linguistic approach",
author = "Cabarr{\~a}o, Vera and
Moniz, Helena and
Batista, Fernando and
Ribeiro, Ricardo and
Mamede, Nuno and
Meinedo, Hugo and
Trancoso, Isabel and
Mata, Ana Isabel and
de Matos, David Martins",
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/1020_Paper.pdf",
pages = "3908--3913",
abstract = "This paper presents a linguistic revision process of a speech corpus of Portuguese broadcast news focusing on metadata annotation for rich transcription, and reports on the impact of the new data on the performance for several modules. The main focus of the revision process consisted on annotating and revising structural metadata events, such as disfluencies and punctuation marks. The resultant revised data is now being extensively used, and was of extreme importance for improving the performance of several modules, especially the punctuation and capitalization modules, but also the speech recognition system, and all the subsequent modules. The resultant data has also been recently used in disfluency studies across domains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cabarrao-etal-2014-revising">
<titleInfo>
<title>Revising the annotation of a Broadcast News corpus: a linguistic approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Cabarrão</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Batista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuno</namePart>
<namePart type="family">Mamede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Meinedo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Trancoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">Isabel</namePart>
<namePart type="family">Mata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Martins</namePart>
<namePart type="family">de Matos</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 presents a linguistic revision process of a speech corpus of Portuguese broadcast news focusing on metadata annotation for rich transcription, and reports on the impact of the new data on the performance for several modules. The main focus of the revision process consisted on annotating and revising structural metadata events, such as disfluencies and punctuation marks. The resultant revised data is now being extensively used, and was of extreme importance for improving the performance of several modules, especially the punctuation and capitalization modules, but also the speech recognition system, and all the subsequent modules. The resultant data has also been recently used in disfluency studies across domains.</abstract>
<identifier type="citekey">cabarrao-etal-2014-revising</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1020_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3908</start>
<end>3913</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revising the annotation of a Broadcast News corpus: a linguistic approach
%A Cabarrão, Vera
%A Moniz, Helena
%A Batista, Fernando
%A Ribeiro, Ricardo
%A Mamede, Nuno
%A Meinedo, Hugo
%A Trancoso, Isabel
%A Mata, Ana Isabel
%A de Matos, David Martins
%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 cabarrao-etal-2014-revising
%X This paper presents a linguistic revision process of a speech corpus of Portuguese broadcast news focusing on metadata annotation for rich transcription, and reports on the impact of the new data on the performance for several modules. The main focus of the revision process consisted on annotating and revising structural metadata events, such as disfluencies and punctuation marks. The resultant revised data is now being extensively used, and was of extreme importance for improving the performance of several modules, especially the punctuation and capitalization modules, but also the speech recognition system, and all the subsequent modules. The resultant data has also been recently used in disfluency studies across domains.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1020_Paper.pdf
%P 3908-3913
Markdown (Informal)
[Revising the annotation of a Broadcast News corpus: a linguistic approach](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1020_Paper.pdf) (Cabarrão et al., LREC 2014)
ACL
- Vera Cabarrão, Helena Moniz, Fernando Batista, Ricardo Ribeiro, Nuno Mamede, Hugo Meinedo, Isabel Trancoso, Ana Isabel Mata, and David Martins de Matos. 2014. Revising the annotation of a Broadcast News corpus: a linguistic approach. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3908–3913, Reykjavik, Iceland. European Language Resources Association (ELRA).