@inproceedings{kasen-etal-2019-tagging,
title = "Tagging a {N}orwegian Dialect Corpus",
author = "K{\aa}sen, Andre and
N{\o}klestad, Anders and
Hagen, Kristin and
Priestley, Joel",
editor = "Hartmann, Mareike and
Plank, Barbara",
booktitle = "Proceedings of the 22nd Nordic Conference on Computational Linguistics",
month = sep # "{--}" # oct,
year = "2019",
address = "Turku, Finland",
publisher = {Link{\"o}ping University Electronic Press},
url = "https://aclanthology.org/W19-6140",
pages = "350--355",
abstract = "This paper describes an evaluation of five data-driven part-of-speech (PoS) taggers for spoken Norwegian. The taggers all rely on different machine learning mechanisms: decision trees, hidden Markov models (HMMs), conditional random fields (CRFs), long-short term memory networks (LSTMs), and convolutional neural networks (CNNs). We go into some of the challenges posed by the task of tagging spoken, as opposed to written, language, and in particular a wide range of dialects as is found in the recordings of the LIA (Language Infrastructure made Accessible) project. The results show that the taggers based on either conditional random fields or neural networks perform much better than the rest, with the LSTM tagger getting the highest score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kasen-etal-2019-tagging">
<titleInfo>
<title>Tagging a Norwegian Dialect Corpus</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">Anders</namePart>
<namePart type="family">Nøklestad</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">Joel</namePart>
<namePart type="family">Priestley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-sep–oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Nordic Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mareike</namePart>
<namePart type="family">Hartmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press</publisher>
<place>
<placeTerm type="text">Turku, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes an evaluation of five data-driven part-of-speech (PoS) taggers for spoken Norwegian. The taggers all rely on different machine learning mechanisms: decision trees, hidden Markov models (HMMs), conditional random fields (CRFs), long-short term memory networks (LSTMs), and convolutional neural networks (CNNs). We go into some of the challenges posed by the task of tagging spoken, as opposed to written, language, and in particular a wide range of dialects as is found in the recordings of the LIA (Language Infrastructure made Accessible) project. The results show that the taggers based on either conditional random fields or neural networks perform much better than the rest, with the LSTM tagger getting the highest score.</abstract>
<identifier type="citekey">kasen-etal-2019-tagging</identifier>
<location>
<url>https://aclanthology.org/W19-6140</url>
</location>
<part>
<date>2019-sep–oct</date>
<extent unit="page">
<start>350</start>
<end>355</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tagging a Norwegian Dialect Corpus
%A Kåsen, Andre
%A Nøklestad, Anders
%A Hagen, Kristin
%A Priestley, Joel
%Y Hartmann, Mareike
%Y Plank, Barbara
%S Proceedings of the 22nd Nordic Conference on Computational Linguistics
%D 2019
%8 sep–oct
%I Linköping University Electronic Press
%C Turku, Finland
%F kasen-etal-2019-tagging
%X This paper describes an evaluation of five data-driven part-of-speech (PoS) taggers for spoken Norwegian. The taggers all rely on different machine learning mechanisms: decision trees, hidden Markov models (HMMs), conditional random fields (CRFs), long-short term memory networks (LSTMs), and convolutional neural networks (CNNs). We go into some of the challenges posed by the task of tagging spoken, as opposed to written, language, and in particular a wide range of dialects as is found in the recordings of the LIA (Language Infrastructure made Accessible) project. The results show that the taggers based on either conditional random fields or neural networks perform much better than the rest, with the LSTM tagger getting the highest score.
%U https://aclanthology.org/W19-6140
%P 350-355
Markdown (Informal)
[Tagging a Norwegian Dialect Corpus](https://aclanthology.org/W19-6140) (Kåsen et al., NoDaLiDa 2019)
ACL
- Andre Kåsen, Anders Nøklestad, Kristin Hagen, and Joel Priestley. 2019. Tagging a Norwegian Dialect Corpus. In Proceedings of the 22nd Nordic Conference on Computational Linguistics, pages 350–355, Turku, Finland. Linköping University Electronic Press.