@inproceedings{blanc-etal-2010-partial,
title = "Partial Parsing of Spontaneous Spoken {F}rench",
author = "Blanc, Olivier and
Constant, Matthieu and
Dister, Anne and
Watrin, Patrick",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/554_Paper.pdf",
abstract = "This paper describes the process and the resources used to automatically annotate a French corpus of spontaneous speech transcriptions in super-chunks. Super-chunks are enhanced chunks that can contain lexical multiword units. This partial parsing is based on a preprocessing stage of the spoken data that consists in reformatting and tagging utterances that break the syntactic structure of the text, such as disfluencies. Spoken specificities were formalized thanks to a systematic linguistic study of a 40-hour-long speech transcription corpus. The chunker uses large-coverage and fine-grained language resources for general written language that have been augmented with resources specific to spoken French. It consists in iteratively applying finite-state lexical and syntactic resources and outputing a finite automaton representing all possible chunk analyses. The best path is then selected thanks to a hybrid disambiguation stage. We show that our system reaches scores that are comparable with state-of-the-art results in the field.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="blanc-etal-2010-partial">
<titleInfo>
<title>Partial Parsing of Spontaneous Spoken French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Blanc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthieu</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Dister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Watrin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the process and the resources used to automatically annotate a French corpus of spontaneous speech transcriptions in super-chunks. Super-chunks are enhanced chunks that can contain lexical multiword units. This partial parsing is based on a preprocessing stage of the spoken data that consists in reformatting and tagging utterances that break the syntactic structure of the text, such as disfluencies. Spoken specificities were formalized thanks to a systematic linguistic study of a 40-hour-long speech transcription corpus. The chunker uses large-coverage and fine-grained language resources for general written language that have been augmented with resources specific to spoken French. It consists in iteratively applying finite-state lexical and syntactic resources and outputing a finite automaton representing all possible chunk analyses. The best path is then selected thanks to a hybrid disambiguation stage. We show that our system reaches scores that are comparable with state-of-the-art results in the field.</abstract>
<identifier type="citekey">blanc-etal-2010-partial</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/554_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Partial Parsing of Spontaneous Spoken French
%A Blanc, Olivier
%A Constant, Matthieu
%A Dister, Anne
%A Watrin, Patrick
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F blanc-etal-2010-partial
%X This paper describes the process and the resources used to automatically annotate a French corpus of spontaneous speech transcriptions in super-chunks. Super-chunks are enhanced chunks that can contain lexical multiword units. This partial parsing is based on a preprocessing stage of the spoken data that consists in reformatting and tagging utterances that break the syntactic structure of the text, such as disfluencies. Spoken specificities were formalized thanks to a systematic linguistic study of a 40-hour-long speech transcription corpus. The chunker uses large-coverage and fine-grained language resources for general written language that have been augmented with resources specific to spoken French. It consists in iteratively applying finite-state lexical and syntactic resources and outputing a finite automaton representing all possible chunk analyses. The best path is then selected thanks to a hybrid disambiguation stage. We show that our system reaches scores that are comparable with state-of-the-art results in the field.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/554_Paper.pdf
Markdown (Informal)
[Partial Parsing of Spontaneous Spoken French](http://www.lrec-conf.org/proceedings/lrec2010/pdf/554_Paper.pdf) (Blanc et al., LREC 2010)
ACL
- Olivier Blanc, Matthieu Constant, Anne Dister, and Patrick Watrin. 2010. Partial Parsing of Spontaneous Spoken French. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).