@inproceedings{bazillon-etal-2012-syntactic,
title = "Syntactic annotation of spontaneous speech: application to call-center conversation data",
author = "Bazillon, Thierry and
Deplano, Melanie and
Bechet, Frederic and
Nasr, Alexis and
Favre, Benoit",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/682_Paper.pdf",
pages = "1338--1342",
abstract = "This paper describes the syntactic annotation process of the DECODA corpus. This corpus contains manual transcriptions of spoken conversations recorded in the French call-center of the Paris Public Transport Authority (RATP). Three levels of syntactic annotation have been performed with a semi-supervised approach: POS tags, Syntactic Chunks and Dependency parses. The main idea is to use off-the-shelf NLP tools and models, originaly developped and trained on written text, to perform a first automatic annotation on the manually transcribed corpus. At the same time a fully manual annotation process is performed on a subset of the original corpus, called the GOLD corpus. An iterative process is then applied, consisting in manually correcting errors found in the automatic annotations, retraining the linguistic models of the NLP tools on this corrected corpus, then checking the quality of the adapted models on the fully manual annotations of the GOLD corpus. This process iterates until a certain error rate is reached. This paper describes this process, the main issues raising when adapting NLP tools to process speech transcriptions, and presents the first evaluations performed with these new adapted tools.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bazillon-etal-2012-syntactic">
<titleInfo>
<title>Syntactic annotation of spontaneous speech: application to call-center conversation data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Bazillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melanie</namePart>
<namePart type="family">Deplano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Bechet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Nasr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoit</namePart>
<namePart type="family">Favre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the syntactic annotation process of the DECODA corpus. This corpus contains manual transcriptions of spoken conversations recorded in the French call-center of the Paris Public Transport Authority (RATP). Three levels of syntactic annotation have been performed with a semi-supervised approach: POS tags, Syntactic Chunks and Dependency parses. The main idea is to use off-the-shelf NLP tools and models, originaly developped and trained on written text, to perform a first automatic annotation on the manually transcribed corpus. At the same time a fully manual annotation process is performed on a subset of the original corpus, called the GOLD corpus. An iterative process is then applied, consisting in manually correcting errors found in the automatic annotations, retraining the linguistic models of the NLP tools on this corrected corpus, then checking the quality of the adapted models on the fully manual annotations of the GOLD corpus. This process iterates until a certain error rate is reached. This paper describes this process, the main issues raising when adapting NLP tools to process speech transcriptions, and presents the first evaluations performed with these new adapted tools.</abstract>
<identifier type="citekey">bazillon-etal-2012-syntactic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/682_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1338</start>
<end>1342</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Syntactic annotation of spontaneous speech: application to call-center conversation data
%A Bazillon, Thierry
%A Deplano, Melanie
%A Bechet, Frederic
%A Nasr, Alexis
%A Favre, Benoit
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F bazillon-etal-2012-syntactic
%X This paper describes the syntactic annotation process of the DECODA corpus. This corpus contains manual transcriptions of spoken conversations recorded in the French call-center of the Paris Public Transport Authority (RATP). Three levels of syntactic annotation have been performed with a semi-supervised approach: POS tags, Syntactic Chunks and Dependency parses. The main idea is to use off-the-shelf NLP tools and models, originaly developped and trained on written text, to perform a first automatic annotation on the manually transcribed corpus. At the same time a fully manual annotation process is performed on a subset of the original corpus, called the GOLD corpus. An iterative process is then applied, consisting in manually correcting errors found in the automatic annotations, retraining the linguistic models of the NLP tools on this corrected corpus, then checking the quality of the adapted models on the fully manual annotations of the GOLD corpus. This process iterates until a certain error rate is reached. This paper describes this process, the main issues raising when adapting NLP tools to process speech transcriptions, and presents the first evaluations performed with these new adapted tools.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/682_Paper.pdf
%P 1338-1342
Markdown (Informal)
[Syntactic annotation of spontaneous speech: application to call-center conversation data](http://www.lrec-conf.org/proceedings/lrec2012/pdf/682_Paper.pdf) (Bazillon et al., LREC 2012)
ACL