@inproceedings{karason-loftsson-2023-part,
title = "Is Part-of-Speech Tagging a Solved Problem for {I}celandic?",
author = {K{\'a}rason, {\"O}rvar and
Loftsson, Hrafn},
editor = {Alum{\"a}e, Tanel and
Fishel, Mark},
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may,
year = "2023",
address = "T{\'o}rshavn, Faroe Islands",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2023.nodalida-1.8",
pages = "71--79",
abstract = "We train and evaluate four Part-of-Speech tagging models for Icelandic. Three are older models that obtained the highest accuracy for Icelandic when they were introduced. The fourth model is of a type that currently reaches state-of-the-art accuracy. We use the most recent version of the MIM-GOLD training/testing corpus, its newest tagset, and augmentation data to obtain results that are comparable between the various models. We examine the accuracy improvements with each model and analyse the errors produced by our transformer model, which is based on a previously published ConvBERT model. For the set of errors that all the models make, and for which they predict the same tag, we extract a random subset for manual inspection. Extrapolating from this subset, we obtain a lower bound estimate on annotation errors in the corpus as well as on some unsolvable tagging errors. We argue that further tagging accuracy gains for Icelandic can still be obtained by fixing the errors in MIM-GOLD and, furthermore, that it should still be possible to squeeze out some small gains from our transformer model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karason-loftsson-2023-part">
<titleInfo>
<title>Is Part-of-Speech Tagging a Solved Problem for Icelandic?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Örvar</namePart>
<namePart type="family">Kárason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanel</namePart>
<namePart type="family">Alumäe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tórshavn, Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We train and evaluate four Part-of-Speech tagging models for Icelandic. Three are older models that obtained the highest accuracy for Icelandic when they were introduced. The fourth model is of a type that currently reaches state-of-the-art accuracy. We use the most recent version of the MIM-GOLD training/testing corpus, its newest tagset, and augmentation data to obtain results that are comparable between the various models. We examine the accuracy improvements with each model and analyse the errors produced by our transformer model, which is based on a previously published ConvBERT model. For the set of errors that all the models make, and for which they predict the same tag, we extract a random subset for manual inspection. Extrapolating from this subset, we obtain a lower bound estimate on annotation errors in the corpus as well as on some unsolvable tagging errors. We argue that further tagging accuracy gains for Icelandic can still be obtained by fixing the errors in MIM-GOLD and, furthermore, that it should still be possible to squeeze out some small gains from our transformer model.</abstract>
<identifier type="citekey">karason-loftsson-2023-part</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.8</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>71</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is Part-of-Speech Tagging a Solved Problem for Icelandic?
%A Kárason, Örvar
%A Loftsson, Hrafn
%Y Alumäe, Tanel
%Y Fishel, Mark
%S Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2023
%8 May
%I University of Tartu Library
%C Tórshavn, Faroe Islands
%F karason-loftsson-2023-part
%X We train and evaluate four Part-of-Speech tagging models for Icelandic. Three are older models that obtained the highest accuracy for Icelandic when they were introduced. The fourth model is of a type that currently reaches state-of-the-art accuracy. We use the most recent version of the MIM-GOLD training/testing corpus, its newest tagset, and augmentation data to obtain results that are comparable between the various models. We examine the accuracy improvements with each model and analyse the errors produced by our transformer model, which is based on a previously published ConvBERT model. For the set of errors that all the models make, and for which they predict the same tag, we extract a random subset for manual inspection. Extrapolating from this subset, we obtain a lower bound estimate on annotation errors in the corpus as well as on some unsolvable tagging errors. We argue that further tagging accuracy gains for Icelandic can still be obtained by fixing the errors in MIM-GOLD and, furthermore, that it should still be possible to squeeze out some small gains from our transformer model.
%U https://aclanthology.org/2023.nodalida-1.8
%P 71-79
Markdown (Informal)
[Is Part-of-Speech Tagging a Solved Problem for Icelandic?](https://aclanthology.org/2023.nodalida-1.8) (Kárason & Loftsson, NoDaLiDa 2023)
ACL