@inproceedings{redeker-etal-2012-multi,
title = "Multi-Layer Discourse Annotation of a {D}utch Text Corpus",
author = "Redeker, Gisela and
Berzl{\'a}novich, Ildik{\'o} and
van der Vliet, Nynke and
Bouma, Gosse and
Egg, Markus",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/887_Paper.pdf",
pages = "2820--2825",
abstract = "We have compiled a corpus of 80 Dutch texts from expository and persuasive genres, which we annotated for rhetorical and genre-specific discourse structure, and lexical cohesion with the goal of creating a gold standard for further research. The annota{\^A}{\neg}tions are based on a segmentation of the text in elementary discourse units that takes into account cues from syntax and punctuation. During the labor-intensive discourse-structure annotation (RST analysis), we took great care to thoroughly reconcile the initial analyses. That process and the availability of two independent initial analyses for each text allows us to analyze our disagreements and to assess the confusability of RST relations, and thereby improve the annotation guidelines and gather evidence for the classification of these relations into larger groups. We are using this resource for corpus-based studies of discourse relations, discourse markers, cohesion, and genre differences, e.g., the question of how discourse structure and lexical cohesion interact for different genres in the overall organization of texts. We are also exploring automatic text segmentation and semi-automatic discourse annotation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="redeker-etal-2012-multi">
<titleInfo>
<title>Multi-Layer Discourse Annotation of a Dutch Text Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gisela</namePart>
<namePart type="family">Redeker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Berzlánovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nynke</namePart>
<namePart type="family">van der Vliet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gosse</namePart>
<namePart type="family">Bouma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Egg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We have compiled a corpus of 80 Dutch texts from expository and persuasive genres, which we annotated for rhetorical and genre-specific discourse structure, and lexical cohesion with the goal of creating a gold standard for further research. The annotaÂʼnegtions are based on a segmentation of the text in elementary discourse units that takes into account cues from syntax and punctuation. During the labor-intensive discourse-structure annotation (RST analysis), we took great care to thoroughly reconcile the initial analyses. That process and the availability of two independent initial analyses for each text allows us to analyze our disagreements and to assess the confusability of RST relations, and thereby improve the annotation guidelines and gather evidence for the classification of these relations into larger groups. We are using this resource for corpus-based studies of discourse relations, discourse markers, cohesion, and genre differences, e.g., the question of how discourse structure and lexical cohesion interact for different genres in the overall organization of texts. We are also exploring automatic text segmentation and semi-automatic discourse annotation.</abstract>
<identifier type="citekey">redeker-etal-2012-multi</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/887_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2820</start>
<end>2825</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Layer Discourse Annotation of a Dutch Text Corpus
%A Redeker, Gisela
%A Berzlánovich, Ildikó
%A van der Vliet, Nynke
%A Bouma, Gosse
%A Egg, Markus
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F redeker-etal-2012-multi
%X We have compiled a corpus of 80 Dutch texts from expository and persuasive genres, which we annotated for rhetorical and genre-specific discourse structure, and lexical cohesion with the goal of creating a gold standard for further research. The annotaÂʼnegtions are based on a segmentation of the text in elementary discourse units that takes into account cues from syntax and punctuation. During the labor-intensive discourse-structure annotation (RST analysis), we took great care to thoroughly reconcile the initial analyses. That process and the availability of two independent initial analyses for each text allows us to analyze our disagreements and to assess the confusability of RST relations, and thereby improve the annotation guidelines and gather evidence for the classification of these relations into larger groups. We are using this resource for corpus-based studies of discourse relations, discourse markers, cohesion, and genre differences, e.g., the question of how discourse structure and lexical cohesion interact for different genres in the overall organization of texts. We are also exploring automatic text segmentation and semi-automatic discourse annotation.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/887_Paper.pdf
%P 2820-2825
Markdown (Informal)
[Multi-Layer Discourse Annotation of a Dutch Text Corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/887_Paper.pdf) (Redeker et al., LREC 2012)
ACL
- Gisela Redeker, Ildikó Berzlánovich, Nynke van der Vliet, Gosse Bouma, and Markus Egg. 2012. Multi-Layer Discourse Annotation of a Dutch Text Corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2820–2825, Istanbul, Turkey. European Language Resources Association (ELRA).