@inproceedings{rosok-dale-2024-nb-uttale,
title = "{NB} Uttale: A {N}orwegian Pronunciation Lexicon with Dialect Variation",
author = "R{\o}sok, Marie Iversdatter and
Dale, Ingerid L{\o}yning",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1056",
pages = "12087--12092",
abstract = "We present a Norwegian pronunciation lexicon with Bokm{\aa}l orthographic word forms and up to eight alternate phonological transcriptions per word form. The lexicon covers dialectal variations for five geographical areas, as well as pronunciation variations for spontaneous and manuscript-read speech. It is based on the NST Bokm{\aa}l lexicon for East Norwegian, whose original phonological transcriptions have been corrected, before they were converted with dialect specific regular expression rules. To evaluate the quality and consistency of the new, rule-generated transcriptions, we trained grapheme-to phoneme (G2P) models and report our results with word- (WER) and phoneme-error-rate (PER) metrics. We found that the G2P models trained on lexica for Southwest and West Norwegian close-to written transcriptions have the lowest WER scores, and that all error-corrected, close-to-written lexica yield better WER scores than the original NST lexicon. The lexicon is available under an open license, and can be used for various language technology applications and in linguistic research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosok-dale-2024-nb-uttale">
<titleInfo>
<title>NB Uttale: A Norwegian Pronunciation Lexicon with Dialect Variation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="given">Iversdatter</namePart>
<namePart type="family">Røsok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingerid</namePart>
<namePart type="given">Løyning</namePart>
<namePart type="family">Dale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a Norwegian pronunciation lexicon with Bokmål orthographic word forms and up to eight alternate phonological transcriptions per word form. The lexicon covers dialectal variations for five geographical areas, as well as pronunciation variations for spontaneous and manuscript-read speech. It is based on the NST Bokmål lexicon for East Norwegian, whose original phonological transcriptions have been corrected, before they were converted with dialect specific regular expression rules. To evaluate the quality and consistency of the new, rule-generated transcriptions, we trained grapheme-to phoneme (G2P) models and report our results with word- (WER) and phoneme-error-rate (PER) metrics. We found that the G2P models trained on lexica for Southwest and West Norwegian close-to written transcriptions have the lowest WER scores, and that all error-corrected, close-to-written lexica yield better WER scores than the original NST lexicon. The lexicon is available under an open license, and can be used for various language technology applications and in linguistic research.</abstract>
<identifier type="citekey">rosok-dale-2024-nb-uttale</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1056</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12087</start>
<end>12092</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NB Uttale: A Norwegian Pronunciation Lexicon with Dialect Variation
%A Røsok, Marie Iversdatter
%A Dale, Ingerid Løyning
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F rosok-dale-2024-nb-uttale
%X We present a Norwegian pronunciation lexicon with Bokmål orthographic word forms and up to eight alternate phonological transcriptions per word form. The lexicon covers dialectal variations for five geographical areas, as well as pronunciation variations for spontaneous and manuscript-read speech. It is based on the NST Bokmål lexicon for East Norwegian, whose original phonological transcriptions have been corrected, before they were converted with dialect specific regular expression rules. To evaluate the quality and consistency of the new, rule-generated transcriptions, we trained grapheme-to phoneme (G2P) models and report our results with word- (WER) and phoneme-error-rate (PER) metrics. We found that the G2P models trained on lexica for Southwest and West Norwegian close-to written transcriptions have the lowest WER scores, and that all error-corrected, close-to-written lexica yield better WER scores than the original NST lexicon. The lexicon is available under an open license, and can be used for various language technology applications and in linguistic research.
%U https://aclanthology.org/2024.lrec-main.1056
%P 12087-12092
Markdown (Informal)
[NB Uttale: A Norwegian Pronunciation Lexicon with Dialect Variation](https://aclanthology.org/2024.lrec-main.1056) (Røsok & Dale, LREC-COLING 2024)
ACL