@inproceedings{stymne-ostman-2022-slanda,
title = {{SL}{\"a}{ND}a version 2.0: Improved and Extended Annotation of Narrative and Dialogue in {S}wedish Literature},
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.570",
pages = "5324--5333",
abstract = {In this paper, we describe version 2.0 of the SL{\"a}NDa corpus. SL{\"a}NDa, the Swedish Literary corpus of Narrative and Dialogue, now contains excerpts from 19 novels, written between 1809{--}1940. The main focus of the SL{\"a}NDa corpus is to distinguish between direct speech and the main narrative. In order to isolate the narrative, we also annotate everything else which does not belong to the narrative, such as thoughts, quotations, and letters. SL{\"a}NDa version 2.0 has a slightly updated annotation scheme from version 1.0. In addition, we added new texts from eleven authors and performed quality control on the previous version. We are specifically interested in different ways of marking speech segments, such as quotation marks, dashes, or no marking at all. To allow a detailed evaluation of this aspect, we added dedicated test sets to SL{\"a}NDa for these different types of speech marking. In a pilot experiment, we explore the impact of typographic speech marking by using these test sets, as well as artificially stripping the training data of speech markers.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stymne-ostman-2022-slanda">
<titleInfo>
<title>SLäNDa version 2.0: Improved and Extended Annotation of Narrative and Dialogue in Swedish Literature</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>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>In this paper, we describe version 2.0 of the SLäNDa corpus. SLäNDa, the Swedish Literary corpus of Narrative and Dialogue, now contains excerpts from 19 novels, written between 1809–1940. The main focus of the SLäNDa corpus is to distinguish between direct speech and the main narrative. In order to isolate the narrative, we also annotate everything else which does not belong to the narrative, such as thoughts, quotations, and letters. SLäNDa version 2.0 has a slightly updated annotation scheme from version 1.0. In addition, we added new texts from eleven authors and performed quality control on the previous version. We are specifically interested in different ways of marking speech segments, such as quotation marks, dashes, or no marking at all. To allow a detailed evaluation of this aspect, we added dedicated test sets to SLäNDa for these different types of speech marking. In a pilot experiment, we explore the impact of typographic speech marking by using these test sets, as well as artificially stripping the training data of speech markers.</abstract>
<identifier type="citekey">stymne-ostman-2022-slanda</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.570</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5324</start>
<end>5333</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SLäNDa version 2.0: Improved and Extended Annotation of Narrative and Dialogue in Swedish Literature
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F stymne-ostman-2022-slanda
%X In this paper, we describe version 2.0 of the SLäNDa corpus. SLäNDa, the Swedish Literary corpus of Narrative and Dialogue, now contains excerpts from 19 novels, written between 1809–1940. The main focus of the SLäNDa corpus is to distinguish between direct speech and the main narrative. In order to isolate the narrative, we also annotate everything else which does not belong to the narrative, such as thoughts, quotations, and letters. SLäNDa version 2.0 has a slightly updated annotation scheme from version 1.0. In addition, we added new texts from eleven authors and performed quality control on the previous version. We are specifically interested in different ways of marking speech segments, such as quotation marks, dashes, or no marking at all. To allow a detailed evaluation of this aspect, we added dedicated test sets to SLäNDa for these different types of speech marking. In a pilot experiment, we explore the impact of typographic speech marking by using these test sets, as well as artificially stripping the training data of speech markers.
%U https://aclanthology.org/2022.lrec-1.570
%P 5324-5333
Markdown (Informal)
[SLäNDa version 2.0: Improved and Extended Annotation of Narrative and Dialogue in Swedish Literature](https://aclanthology.org/2022.lrec-1.570) (Stymne & Östman, LREC 2022)
ACL