@inproceedings{wang-etal-2020-odil,
title = "{ODIL}{\_}{S}yntax: a Free Spontaneous Spoken {F}rench Treebank Annotated with Constituent Trees",
author = {Wang, Ilaine and
Pelletier, Aurore and
Antoine, Jean-Yves and
Halftermeyer, Ana{\"\i}s},
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.652",
pages = "5301--5307",
abstract = "This paper describes ODIL Syntax, a French treebank built on spontaneous speech transcripts. The syntactic structure of every speech turn is represented by constituent trees, through a procedure which combines an automatic annotation provided by a parser (here, the Stanford Parser) and a manual revision. ODIL Syntax respects the annotation scheme designed for the French TreeBank (FTB), with the addition of some annotation guidelines that aims at representing specific features of the spoken language such as speech disfluencies. The corpus will be freely distributed by January 2020 under a Creative Commons licence. It will ground a further semantic enrichment dedicated to the representation of temporal entities and temporal relations, as a second phase of the ODIL@Temporal project. The paper details the annotation scheme we followed with a emphasis on the representation of speech disfluencies. We then present the annotation procedure that was carried out on the Contemplata annotation platform. In the last section, we provide some distributional characteristics of the annotated corpus (POS distribution, multiword expressions).",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2020-odil">
<titleInfo>
<title>ODIL_Syntax: a Free Spontaneous Spoken French Treebank Annotated with Constituent Trees</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilaine</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurore</namePart>
<namePart type="family">Pelletier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Anaïs</namePart>
<namePart type="family">Halftermeyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This paper describes ODIL Syntax, a French treebank built on spontaneous speech transcripts. The syntactic structure of every speech turn is represented by constituent trees, through a procedure which combines an automatic annotation provided by a parser (here, the Stanford Parser) and a manual revision. ODIL Syntax respects the annotation scheme designed for the French TreeBank (FTB), with the addition of some annotation guidelines that aims at representing specific features of the spoken language such as speech disfluencies. The corpus will be freely distributed by January 2020 under a Creative Commons licence. It will ground a further semantic enrichment dedicated to the representation of temporal entities and temporal relations, as a second phase of the ODIL@Temporal project. The paper details the annotation scheme we followed with a emphasis on the representation of speech disfluencies. We then present the annotation procedure that was carried out on the Contemplata annotation platform. In the last section, we provide some distributional characteristics of the annotated corpus (POS distribution, multiword expressions).</abstract>
<identifier type="citekey">wang-etal-2020-odil</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.652</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>5301</start>
<end>5307</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ODIL_Syntax: a Free Spontaneous Spoken French Treebank Annotated with Constituent Trees
%A Wang, Ilaine
%A Pelletier, Aurore
%A Antoine, Jean-Yves
%A Halftermeyer, Anaïs
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F wang-etal-2020-odil
%X This paper describes ODIL Syntax, a French treebank built on spontaneous speech transcripts. The syntactic structure of every speech turn is represented by constituent trees, through a procedure which combines an automatic annotation provided by a parser (here, the Stanford Parser) and a manual revision. ODIL Syntax respects the annotation scheme designed for the French TreeBank (FTB), with the addition of some annotation guidelines that aims at representing specific features of the spoken language such as speech disfluencies. The corpus will be freely distributed by January 2020 under a Creative Commons licence. It will ground a further semantic enrichment dedicated to the representation of temporal entities and temporal relations, as a second phase of the ODIL@Temporal project. The paper details the annotation scheme we followed with a emphasis on the representation of speech disfluencies. We then present the annotation procedure that was carried out on the Contemplata annotation platform. In the last section, we provide some distributional characteristics of the annotated corpus (POS distribution, multiword expressions).
%U https://aclanthology.org/2020.lrec-1.652
%P 5301-5307
Markdown (Informal)
[ODIL_Syntax: a Free Spontaneous Spoken French Treebank Annotated with Constituent Trees](https://aclanthology.org/2020.lrec-1.652) (Wang et al., LREC 2020)
ACL