@inproceedings{afantenos-etal-2010-learning,
title = "Learning Recursive Segments for Discourse Parsing",
author = "Afantenos, Stergos and
Denis, Pascal and
Muller, Philippe and
Danlos, Laurence",
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/582_Paper.pdf",
abstract = "Automatically detecting discourse segments is an important preliminary step towards full discourse parsing. Previous research on discourse segmentation have relied on the assumption that elementary discourse units (EDUs) in a document always form a linear sequence (i.e., they can never be nested). Unfortunately, this assumption turns out to be too strong, for some theories of discourse, like the ''``Segmented Discourse Representation Theory'''' or SDRT, allow for nested discourse units. In this paper, we present a simple approach to discourse segmentation that is able to produce nested EDUs. Our approach builds on standard multi-class classification techniques making use of a regularized maximum entropy model, combined with a simple repairing heuristic that enforces global coherence. Our system was developed and evaluated on the first round of annotations provided by the French Annodis project (an ongoing effort to create a discourse bank for French). Cross-validated on only 47 documents (1,445 EDUs), our system achieves encouraging performance results with an F-score of 73{\%} for finding EDUs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="afantenos-etal-2010-learning">
<titleInfo>
<title>Learning Recursive Segments for Discourse Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stergos</namePart>
<namePart type="family">Afantenos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascal</namePart>
<namePart type="family">Denis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Muller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurence</namePart>
<namePart type="family">Danlos</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>Automatically detecting discourse segments is an important preliminary step towards full discourse parsing. Previous research on discourse segmentation have relied on the assumption that elementary discourse units (EDUs) in a document always form a linear sequence (i.e., they can never be nested). Unfortunately, this assumption turns out to be too strong, for some theories of discourse, like the ”“Segmented Discourse Representation Theory”” or SDRT, allow for nested discourse units. In this paper, we present a simple approach to discourse segmentation that is able to produce nested EDUs. Our approach builds on standard multi-class classification techniques making use of a regularized maximum entropy model, combined with a simple repairing heuristic that enforces global coherence. Our system was developed and evaluated on the first round of annotations provided by the French Annodis project (an ongoing effort to create a discourse bank for French). Cross-validated on only 47 documents (1,445 EDUs), our system achieves encouraging performance results with an F-score of 73% for finding EDUs.</abstract>
<identifier type="citekey">afantenos-etal-2010-learning</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/582_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Recursive Segments for Discourse Parsing
%A Afantenos, Stergos
%A Denis, Pascal
%A Muller, Philippe
%A Danlos, Laurence
%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 afantenos-etal-2010-learning
%X Automatically detecting discourse segments is an important preliminary step towards full discourse parsing. Previous research on discourse segmentation have relied on the assumption that elementary discourse units (EDUs) in a document always form a linear sequence (i.e., they can never be nested). Unfortunately, this assumption turns out to be too strong, for some theories of discourse, like the ”“Segmented Discourse Representation Theory”” or SDRT, allow for nested discourse units. In this paper, we present a simple approach to discourse segmentation that is able to produce nested EDUs. Our approach builds on standard multi-class classification techniques making use of a regularized maximum entropy model, combined with a simple repairing heuristic that enforces global coherence. Our system was developed and evaluated on the first round of annotations provided by the French Annodis project (an ongoing effort to create a discourse bank for French). Cross-validated on only 47 documents (1,445 EDUs), our system achieves encouraging performance results with an F-score of 73% for finding EDUs.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/582_Paper.pdf
Markdown (Informal)
[Learning Recursive Segments for Discourse Parsing](http://www.lrec-conf.org/proceedings/lrec2010/pdf/582_Paper.pdf) (Afantenos et al., LREC 2010)
ACL
- Stergos Afantenos, Pascal Denis, Philippe Muller, and Laurence Danlos. 2010. Learning Recursive Segments for Discourse Parsing. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).