@inproceedings{antoine-etal-2008-automatic,
title = "Automatic Rich Annotation of Large Corpus of Conversational transcribed speech: the Chunking Task of the {EPAC} Project",
author = "Antoine, Jean-Yves and
Mokrane, Abdenour and
Friburger, Nathalie",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/172_paper.pdf",
abstract = "This paper describes the use of the CasSys platform in order to achieve the chunking of conversational speech transcripts by means of cascades of Unitex transducers. Our system is involved in the EPAC project of the French National agency of Research (ANR). The aim of this project is to develop robust methods for the annotation of audio/multimedia document collections which contains conversational speech sequences such as TV or radio programs. At first, this paper presents the EPAC project and the adaptation of a former chunking system (Romus) which was developed in the restricted framework of dedicated spoken man-machine dialogue. Then, it describes the problems that are arising due to 1) spontaneous speech disfluencies and 2) errors for the previous stages of processing (automatic speech recognition and POS tagging).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="antoine-etal-2008-automatic">
<titleInfo>
<title>Automatic Rich Annotation of Large Corpus of Conversational transcribed speech: the Chunking Task of the EPAC Project</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jean-Yves</namePart>
<namePart type="family">Antoine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdenour</namePart>
<namePart type="family">Mokrane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathalie</namePart>
<namePart type="family">Friburger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the use of the CasSys platform in order to achieve the chunking of conversational speech transcripts by means of cascades of Unitex transducers. Our system is involved in the EPAC project of the French National agency of Research (ANR). The aim of this project is to develop robust methods for the annotation of audio/multimedia document collections which contains conversational speech sequences such as TV or radio programs. At first, this paper presents the EPAC project and the adaptation of a former chunking system (Romus) which was developed in the restricted framework of dedicated spoken man-machine dialogue. Then, it describes the problems that are arising due to 1) spontaneous speech disfluencies and 2) errors for the previous stages of processing (automatic speech recognition and POS tagging).</abstract>
<identifier type="citekey">antoine-etal-2008-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/172_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Rich Annotation of Large Corpus of Conversational transcribed speech: the Chunking Task of the EPAC Project
%A Antoine, Jean-Yves
%A Mokrane, Abdenour
%A Friburger, Nathalie
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F antoine-etal-2008-automatic
%X This paper describes the use of the CasSys platform in order to achieve the chunking of conversational speech transcripts by means of cascades of Unitex transducers. Our system is involved in the EPAC project of the French National agency of Research (ANR). The aim of this project is to develop robust methods for the annotation of audio/multimedia document collections which contains conversational speech sequences such as TV or radio programs. At first, this paper presents the EPAC project and the adaptation of a former chunking system (Romus) which was developed in the restricted framework of dedicated spoken man-machine dialogue. Then, it describes the problems that are arising due to 1) spontaneous speech disfluencies and 2) errors for the previous stages of processing (automatic speech recognition and POS tagging).
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/172_paper.pdf
Markdown (Informal)
[Automatic Rich Annotation of Large Corpus of Conversational transcribed speech: the Chunking Task of the EPAC Project](http://www.lrec-conf.org/proceedings/lrec2008/pdf/172_paper.pdf) (Antoine et al., LREC 2008)
ACL