@inproceedings{bick-etal-2012-annotation,
title = "The annotation of the {C}-{ORAL}-{BRASIL} oral through the implementation of the Palavras Parser",
author = "Bick, Eckhard and
Mello, Heliana and
Panunzi, Alessandro and
Raso, Tommaso",
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/586_Paper.pdf",
pages = "3382--3386",
abstract = "This article describes the morphosyntactic annotation of the C-ORAL-BRASIL speech corpus, using an adapted version of the Palavras parser. In order to achieve compatibility with annotation rules designed for standard written Portuguese, transcribed words were orthographically normalized, and the parsing lexicon augmented with speech-specific material, phonetically spelled abbreviations etc. Using a two-level annotation approach, speech flow markers like overlaps, retractions and non-verbal productions were separated from running, annotatable text. In the absence of punctuation, syntactic segmentation was achieved by exploiting prosodic break markers, enhanced by a rule-based distinctions between pause and break functions. Under optimal conditions, the modified parsing system achieved correctness rates (F-scores) of 98.6{\%} for part of speech, 95{\%} for syntactic function and 99{\%} for lemmatization. Especially at the syntactic level, a clear connection between accessibility of prosodic break markers and annotation performance could be documented.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bick-etal-2012-annotation">
<titleInfo>
<title>The annotation of the C-ORAL-BRASIL oral through the implementation of the Palavras Parser</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eckhard</namePart>
<namePart type="family">Bick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heliana</namePart>
<namePart type="family">Mello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Panunzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Raso</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 article describes the morphosyntactic annotation of the C-ORAL-BRASIL speech corpus, using an adapted version of the Palavras parser. In order to achieve compatibility with annotation rules designed for standard written Portuguese, transcribed words were orthographically normalized, and the parsing lexicon augmented with speech-specific material, phonetically spelled abbreviations etc. Using a two-level annotation approach, speech flow markers like overlaps, retractions and non-verbal productions were separated from running, annotatable text. In the absence of punctuation, syntactic segmentation was achieved by exploiting prosodic break markers, enhanced by a rule-based distinctions between pause and break functions. Under optimal conditions, the modified parsing system achieved correctness rates (F-scores) of 98.6% for part of speech, 95% for syntactic function and 99% for lemmatization. Especially at the syntactic level, a clear connection between accessibility of prosodic break markers and annotation performance could be documented.</abstract>
<identifier type="citekey">bick-etal-2012-annotation</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/586_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3382</start>
<end>3386</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The annotation of the C-ORAL-BRASIL oral through the implementation of the Palavras Parser
%A Bick, Eckhard
%A Mello, Heliana
%A Panunzi, Alessandro
%A Raso, Tommaso
%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 bick-etal-2012-annotation
%X This article describes the morphosyntactic annotation of the C-ORAL-BRASIL speech corpus, using an adapted version of the Palavras parser. In order to achieve compatibility with annotation rules designed for standard written Portuguese, transcribed words were orthographically normalized, and the parsing lexicon augmented with speech-specific material, phonetically spelled abbreviations etc. Using a two-level annotation approach, speech flow markers like overlaps, retractions and non-verbal productions were separated from running, annotatable text. In the absence of punctuation, syntactic segmentation was achieved by exploiting prosodic break markers, enhanced by a rule-based distinctions between pause and break functions. Under optimal conditions, the modified parsing system achieved correctness rates (F-scores) of 98.6% for part of speech, 95% for syntactic function and 99% for lemmatization. Especially at the syntactic level, a clear connection between accessibility of prosodic break markers and annotation performance could be documented.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/586_Paper.pdf
%P 3382-3386
Markdown (Informal)
[The annotation of the C-ORAL-BRASIL oral through the implementation of the Palavras Parser](http://www.lrec-conf.org/proceedings/lrec2012/pdf/586_Paper.pdf) (Bick et al., LREC 2012)
ACL