@inproceedings{santos-etal-2014-corpus,
title = "A corpus of {E}uropean {P}ortuguese child and child-directed speech",
author = "Santos, Ana L{\'u}cia and
G{\'e}n{\'e}reux, Michel and
Cardoso, Aida and
Agostinho, Celina and
Abalada, Silvana",
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/514_Paper.pdf",
pages = "1488--1491",
abstract = "We present a corpus of child and child-directed speech of European Portuguese. This corpus results from the expansion of an already existing database (Santos, 2006). It includes around 52 hours of child-adult interaction and now contains 27,595 child utterances and 70,736 adult utterances. The corpus was transcribed according to the CHILDES system (Child Language Data Exchange System) and using the CLAN software (MacWhinney, 2000). The corpus itself represents a valuable resource for the study of lexical, syntax and discourse acquisition. In this paper, we also show how we used an existing part-of-speech tagger trained on written material (G{\'e}n{\'e}reux, Hendrickx {\&} Mendes, 2012) to automatically lemmatize and tag child and child-directed speech and generate a line with part-of-speech information compatible with the CLAN interface. We show that a POS-tagger trained on the analysis of written language can be exploited for the treatment of spoken material with minimal effort, with only a small number of written rules assisting the statistical model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="santos-etal-2014-corpus">
<titleInfo>
<title>A corpus of European Portuguese child and child-directed speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">Lúcia</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Généreux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Cardoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Celina</namePart>
<namePart type="family">Agostinho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvana</namePart>
<namePart type="family">Abalada</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>We present a corpus of child and child-directed speech of European Portuguese. This corpus results from the expansion of an already existing database (Santos, 2006). It includes around 52 hours of child-adult interaction and now contains 27,595 child utterances and 70,736 adult utterances. The corpus was transcribed according to the CHILDES system (Child Language Data Exchange System) and using the CLAN software (MacWhinney, 2000). The corpus itself represents a valuable resource for the study of lexical, syntax and discourse acquisition. In this paper, we also show how we used an existing part-of-speech tagger trained on written material (Généreux, Hendrickx & Mendes, 2012) to automatically lemmatize and tag child and child-directed speech and generate a line with part-of-speech information compatible with the CLAN interface. We show that a POS-tagger trained on the analysis of written language can be exploited for the treatment of spoken material with minimal effort, with only a small number of written rules assisting the statistical model.</abstract>
<identifier type="citekey">santos-etal-2014-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/514_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1488</start>
<end>1491</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A corpus of European Portuguese child and child-directed speech
%A Santos, Ana Lúcia
%A Généreux, Michel
%A Cardoso, Aida
%A Agostinho, Celina
%A Abalada, Silvana
%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 santos-etal-2014-corpus
%X We present a corpus of child and child-directed speech of European Portuguese. This corpus results from the expansion of an already existing database (Santos, 2006). It includes around 52 hours of child-adult interaction and now contains 27,595 child utterances and 70,736 adult utterances. The corpus was transcribed according to the CHILDES system (Child Language Data Exchange System) and using the CLAN software (MacWhinney, 2000). The corpus itself represents a valuable resource for the study of lexical, syntax and discourse acquisition. In this paper, we also show how we used an existing part-of-speech tagger trained on written material (Généreux, Hendrickx & Mendes, 2012) to automatically lemmatize and tag child and child-directed speech and generate a line with part-of-speech information compatible with the CLAN interface. We show that a POS-tagger trained on the analysis of written language can be exploited for the treatment of spoken material with minimal effort, with only a small number of written rules assisting the statistical model.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/514_Paper.pdf
%P 1488-1491
Markdown (Informal)
[A corpus of European Portuguese child and child-directed speech](http://www.lrec-conf.org/proceedings/lrec2014/pdf/514_Paper.pdf) (Santos et al., LREC 2014)
ACL
- Ana Lúcia Santos, Michel Généreux, Aida Cardoso, Celina Agostinho, and Silvana Abalada. 2014. A corpus of European Portuguese child and child-directed speech. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1488–1491, Reykjavik, Iceland. European Language Resources Association (ELRA).