@inproceedings{simonsen-etal-2026-bragd,
title = "{BRAGD}: Constrained Multi-Label {POS} Tagging for {F}aroese",
author = "Simonsen, Annika and
Scalvini, Barbara and
Johannesen, Uni and
Debess, Iben Nyholm and
Einarsson, Hafsteinn and
Sn{\ae}bjarnarson, V{\'e}steinn",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.913/",
doi = "10.63317/4ibuz9yubt3c",
pages = "11650--11668",
abstract = "We present the first multi-label part-of-speech (POS) tagger for Faroese using linguistically-informed constraints, addressing the data sparsity problem inherent in compound tag approaches. We propose the BRAGD tagset, which decomposes compound morphological tags into independent features (word class, gender, number, case, etc.). The BRAGD tagset is the third iteration of a tagset previously released for Faroese, with substantial modifications that are better aligned with Faroese grammar. We annotate the previously released Sosialurin corpus with the tagset, as well as a new annotated out-of-domain test corpus of 500 sentences from more varied and contemporary texts. To train the tagger, we use a constrained loss function that dynamically masks morphologically invalid features based on the word class (noun, verb, adjective, etc.). We fine-tune a Scandinavian transformer language model using the constrained multi-label loss, achieving an overall accuracy of 97.5{\%}. We find that models trained with multi-label loss perform better, converge faster, and show significantly lower error rates on out-of-domain data than single-label approaches or previously reported methods for Faroese POS tagging. This confirms that the multi-label approach learns robust morphological patterns rather than memorizing domain-specific tag distributions. We release models, code, and the systematically revised Sosialurin-BRAGD corpus, featuring the new BRAGD tagset and a new out-of-domain evaluation corpus from diverse and contemporary text types."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simonsen-etal-2026-bragd">
<titleInfo>
<title>BRAGD: Constrained Multi-Label POS Tagging for Faroese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annika</namePart>
<namePart type="family">Simonsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uni</namePart>
<namePart type="family">Johannesen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iben</namePart>
<namePart type="given">Nyholm</namePart>
<namePart type="family">Debess</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hafsteinn</namePart>
<namePart type="family">Einarsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vésteinn</namePart>
<namePart type="family">Snæbjarnarson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the first multi-label part-of-speech (POS) tagger for Faroese using linguistically-informed constraints, addressing the data sparsity problem inherent in compound tag approaches. We propose the BRAGD tagset, which decomposes compound morphological tags into independent features (word class, gender, number, case, etc.). The BRAGD tagset is the third iteration of a tagset previously released for Faroese, with substantial modifications that are better aligned with Faroese grammar. We annotate the previously released Sosialurin corpus with the tagset, as well as a new annotated out-of-domain test corpus of 500 sentences from more varied and contemporary texts. To train the tagger, we use a constrained loss function that dynamically masks morphologically invalid features based on the word class (noun, verb, adjective, etc.). We fine-tune a Scandinavian transformer language model using the constrained multi-label loss, achieving an overall accuracy of 97.5%. We find that models trained with multi-label loss perform better, converge faster, and show significantly lower error rates on out-of-domain data than single-label approaches or previously reported methods for Faroese POS tagging. This confirms that the multi-label approach learns robust morphological patterns rather than memorizing domain-specific tag distributions. We release models, code, and the systematically revised Sosialurin-BRAGD corpus, featuring the new BRAGD tagset and a new out-of-domain evaluation corpus from diverse and contemporary text types.</abstract>
<identifier type="citekey">simonsen-etal-2026-bragd</identifier>
<identifier type="doi">10.63317/4ibuz9yubt3c</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.913/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11650</start>
<end>11668</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BRAGD: Constrained Multi-Label POS Tagging for Faroese
%A Simonsen, Annika
%A Scalvini, Barbara
%A Johannesen, Uni
%A Debess, Iben Nyholm
%A Einarsson, Hafsteinn
%A Snæbjarnarson, Vésteinn
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F simonsen-etal-2026-bragd
%X We present the first multi-label part-of-speech (POS) tagger for Faroese using linguistically-informed constraints, addressing the data sparsity problem inherent in compound tag approaches. We propose the BRAGD tagset, which decomposes compound morphological tags into independent features (word class, gender, number, case, etc.). The BRAGD tagset is the third iteration of a tagset previously released for Faroese, with substantial modifications that are better aligned with Faroese grammar. We annotate the previously released Sosialurin corpus with the tagset, as well as a new annotated out-of-domain test corpus of 500 sentences from more varied and contemporary texts. To train the tagger, we use a constrained loss function that dynamically masks morphologically invalid features based on the word class (noun, verb, adjective, etc.). We fine-tune a Scandinavian transformer language model using the constrained multi-label loss, achieving an overall accuracy of 97.5%. We find that models trained with multi-label loss perform better, converge faster, and show significantly lower error rates on out-of-domain data than single-label approaches or previously reported methods for Faroese POS tagging. This confirms that the multi-label approach learns robust morphological patterns rather than memorizing domain-specific tag distributions. We release models, code, and the systematically revised Sosialurin-BRAGD corpus, featuring the new BRAGD tagset and a new out-of-domain evaluation corpus from diverse and contemporary text types.
%R 10.63317/4ibuz9yubt3c
%U https://aclanthology.org/2026.lrec-1.913/
%U https://doi.org/10.63317/4ibuz9yubt3c
%P 11650-11668
Markdown (Informal)
[BRAGD: Constrained Multi-Label POS Tagging for Faroese](https://aclanthology.org/2026.lrec-1.913/) (Simonsen et al., LREC 2026)
ACL
- Annika Simonsen, Barbara Scalvini, Uni Johannesen, Iben Nyholm Debess, Hafsteinn Einarsson, and Vésteinn Snæbjarnarson. 2026. BRAGD: Constrained Multi-Label POS Tagging for Faroese. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 11650–11668, Palma de Mallorca, Spain. ELRA Language Resource Association.