@inproceedings{kasen-etal-2022-norwegian,
title = "The {N}orwegian Dialect Corpus Treebank",
author = "K{\aa}sen, Andre and
Hagen, Kristin and
N{\o}klestad, Anders and
Priestly, Joel and
Solberg, Per Erik and
Haug, Dag Trygve Truslew",
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-1.516",
pages = "4827--4832",
abstract = "This paper presents the NDC Treebank of spoken Norwegian dialects in the Bokm{\aa}l variety of Norwegian. It consists of dialect recordings made between 2006 and 2012 which have been digitised, segmented, transcribed and subsequently annotated with morphological and syntactic analysis. The nature of the spoken data gives rise to various challenges both in segmentation and annotation. We follow earlier efforts for Norwegian, in particular the LIA Treebank of spoken dialects transcribed in the Nynorsk variety of Norwegian, in the annotation principles to ensure interusability of the resources. We have developed a spoken language parser on the basis of the annotated material and report on its accuracy both on a test set across the dialects and by holding out single dialects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kasen-etal-2022-norwegian">
<titleInfo>
<title>The Norwegian Dialect Corpus Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Kåsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristin</namePart>
<namePart type="family">Hagen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Nøklestad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Priestly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Per</namePart>
<namePart type="given">Erik</namePart>
<namePart type="family">Solberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dag</namePart>
<namePart type="given">Trygve</namePart>
<namePart type="given">Truslew</namePart>
<namePart type="family">Haug</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>This paper presents the NDC Treebank of spoken Norwegian dialects in the Bokmål variety of Norwegian. It consists of dialect recordings made between 2006 and 2012 which have been digitised, segmented, transcribed and subsequently annotated with morphological and syntactic analysis. The nature of the spoken data gives rise to various challenges both in segmentation and annotation. We follow earlier efforts for Norwegian, in particular the LIA Treebank of spoken dialects transcribed in the Nynorsk variety of Norwegian, in the annotation principles to ensure interusability of the resources. We have developed a spoken language parser on the basis of the annotated material and report on its accuracy both on a test set across the dialects and by holding out single dialects.</abstract>
<identifier type="citekey">kasen-etal-2022-norwegian</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.516</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4827</start>
<end>4832</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Norwegian Dialect Corpus Treebank
%A Kåsen, Andre
%A Hagen, Kristin
%A Nøklestad, Anders
%A Priestly, Joel
%A Solberg, Per Erik
%A Haug, Dag Trygve Truslew
%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 kasen-etal-2022-norwegian
%X This paper presents the NDC Treebank of spoken Norwegian dialects in the Bokmål variety of Norwegian. It consists of dialect recordings made between 2006 and 2012 which have been digitised, segmented, transcribed and subsequently annotated with morphological and syntactic analysis. The nature of the spoken data gives rise to various challenges both in segmentation and annotation. We follow earlier efforts for Norwegian, in particular the LIA Treebank of spoken dialects transcribed in the Nynorsk variety of Norwegian, in the annotation principles to ensure interusability of the resources. We have developed a spoken language parser on the basis of the annotated material and report on its accuracy both on a test set across the dialects and by holding out single dialects.
%U https://aclanthology.org/2022.lrec-1.516
%P 4827-4832
Markdown (Informal)
[The Norwegian Dialect Corpus Treebank](https://aclanthology.org/2022.lrec-1.516) (Kåsen et al., LREC 2022)
ACL
- Andre Kåsen, Kristin Hagen, Anders Nøklestad, Joel Priestly, Per Erik Solberg, and Dag Trygve Truslew Haug. 2022. The Norwegian Dialect Corpus Treebank. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 4827–4832, Marseille, France. European Language Resources Association.