@inproceedings{garcia-fernandez-etal-2014-construction,
title = "Construction and Annotation of a {F}rench Folkstale Corpus",
author = "Garcia-Fernandez, Anne and
Ligozat, Anne-Laure and
Vilnat, Anne",
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/1070_Paper.pdf",
pages = "2430--2435",
abstract = "In this paper, we present the digitization and annotation of a tales corpus - which is to our knowledge the only French tales corpus available and classified according to the Aarne{\&}Thompson classification - composed of historical texts (with old French parts). We first studied whether the pre-processing tools, namely OCR and PoS-tagging, have good enough accuracies to allow automatic analysis. We also manually annotated this corpus according to several types of information which could prove useful for future work: character references, episodes, and motifs. The contributions are the creation of an corpus of French tales from classical anthropology material, which will be made available to the community; the evaluation of OCR and NLP tools on this corpus; and the annotation with anthropological information.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-fernandez-etal-2014-construction">
<titleInfo>
<title>Construction and Annotation of a French Folkstale Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Garcia-Fernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Laure</namePart>
<namePart type="family">Ligozat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Vilnat</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>In this paper, we present the digitization and annotation of a tales corpus - which is to our knowledge the only French tales corpus available and classified according to the Aarne&Thompson classification - composed of historical texts (with old French parts). We first studied whether the pre-processing tools, namely OCR and PoS-tagging, have good enough accuracies to allow automatic analysis. We also manually annotated this corpus according to several types of information which could prove useful for future work: character references, episodes, and motifs. The contributions are the creation of an corpus of French tales from classical anthropology material, which will be made available to the community; the evaluation of OCR and NLP tools on this corpus; and the annotation with anthropological information.</abstract>
<identifier type="citekey">garcia-fernandez-etal-2014-construction</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1070_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2430</start>
<end>2435</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Construction and Annotation of a French Folkstale Corpus
%A Garcia-Fernandez, Anne
%A Ligozat, Anne-Laure
%A Vilnat, Anne
%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 garcia-fernandez-etal-2014-construction
%X In this paper, we present the digitization and annotation of a tales corpus - which is to our knowledge the only French tales corpus available and classified according to the Aarne&Thompson classification - composed of historical texts (with old French parts). We first studied whether the pre-processing tools, namely OCR and PoS-tagging, have good enough accuracies to allow automatic analysis. We also manually annotated this corpus according to several types of information which could prove useful for future work: character references, episodes, and motifs. The contributions are the creation of an corpus of French tales from classical anthropology material, which will be made available to the community; the evaluation of OCR and NLP tools on this corpus; and the annotation with anthropological information.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1070_Paper.pdf
%P 2430-2435
Markdown (Informal)
[Construction and Annotation of a French Folkstale Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1070_Paper.pdf) (Garcia-Fernandez et al., LREC 2014)
ACL
- Anne Garcia-Fernandez, Anne-Laure Ligozat, and Anne Vilnat. 2014. Construction and Annotation of a French Folkstale Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2430–2435, Reykjavik, Iceland. European Language Resources Association (ELRA).