@inproceedings{stymne-ostman-2020-slanda,
title = {{SL}{\"a}{ND}a: An Annotated Corpus of Narrative and Dialogue in {S}wedish Literary Fiction},
author = {Stymne, Sara and
{\"O}stman, Carin},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.103",
pages = "826--834",
abstract = {We describe a new corpus, SL{\"a}NDa, the Swedish Literary corpus of Narrative and Dialogue. It contains Swedish literary fiction, which has been manually annotated for cited materials, with a focus on dialogue. The annotation covers excerpts from eight Swedish novels written between 1879{--}1940, a period of modernization of the Swedish language. SL{\"a}NDa contains annotations for all cited materials that are separate from the main narrative, like quotations and signs. The main focus is on dialogue, for which we annotate speech segments, speech tags, and speakers. In this paper we describe the annotation protocol and procedure and show that we can reach a high inter-annotator agreement. In total, SL{\"a}NDa contains annotations of 44 chapters with over 220K tokens. The annotation identified 4,733 instances of cited material and 1,143 named speaker{--}speech mappings. The corpus is useful for developing computational tools for different types of analysis of literary narrative and speech. We perform a small pilot study where we show how our annotation can help in analyzing language change in Swedish. We find that a number of common function words have their modern version appear earlier in speech than in narrative.},
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="stymne-ostman-2020-slanda">
<titleInfo>
<title>SLäNDa: An Annotated Corpus of Narrative and Dialogue in Swedish Literary Fiction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carin</namePart>
<namePart type="family">Östman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</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 Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</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>We describe a new corpus, SLäNDa, the Swedish Literary corpus of Narrative and Dialogue. It contains Swedish literary fiction, which has been manually annotated for cited materials, with a focus on dialogue. The annotation covers excerpts from eight Swedish novels written between 1879–1940, a period of modernization of the Swedish language. SLäNDa contains annotations for all cited materials that are separate from the main narrative, like quotations and signs. The main focus is on dialogue, for which we annotate speech segments, speech tags, and speakers. In this paper we describe the annotation protocol and procedure and show that we can reach a high inter-annotator agreement. In total, SLäNDa contains annotations of 44 chapters with over 220K tokens. The annotation identified 4,733 instances of cited material and 1,143 named speaker–speech mappings. The corpus is useful for developing computational tools for different types of analysis of literary narrative and speech. We perform a small pilot study where we show how our annotation can help in analyzing language change in Swedish. We find that a number of common function words have their modern version appear earlier in speech than in narrative.</abstract>
<identifier type="citekey">stymne-ostman-2020-slanda</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.103</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>826</start>
<end>834</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SLäNDa: An Annotated Corpus of Narrative and Dialogue in Swedish Literary Fiction
%A Stymne, Sara
%A Östman, Carin
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth 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 stymne-ostman-2020-slanda
%X We describe a new corpus, SLäNDa, the Swedish Literary corpus of Narrative and Dialogue. It contains Swedish literary fiction, which has been manually annotated for cited materials, with a focus on dialogue. The annotation covers excerpts from eight Swedish novels written between 1879–1940, a period of modernization of the Swedish language. SLäNDa contains annotations for all cited materials that are separate from the main narrative, like quotations and signs. The main focus is on dialogue, for which we annotate speech segments, speech tags, and speakers. In this paper we describe the annotation protocol and procedure and show that we can reach a high inter-annotator agreement. In total, SLäNDa contains annotations of 44 chapters with over 220K tokens. The annotation identified 4,733 instances of cited material and 1,143 named speaker–speech mappings. The corpus is useful for developing computational tools for different types of analysis of literary narrative and speech. We perform a small pilot study where we show how our annotation can help in analyzing language change in Swedish. We find that a number of common function words have their modern version appear earlier in speech than in narrative.
%U https://aclanthology.org/2020.lrec-1.103
%P 826-834
Markdown (Informal)
[SLäNDa: An Annotated Corpus of Narrative and Dialogue in Swedish Literary Fiction](https://aclanthology.org/2020.lrec-1.103) (Stymne & Östman, LREC 2020)
ACL