@inproceedings{morad-etal-2024-part,
title = "Part-of-Speech Tagging for {N}orthern {K}urdish",
author = "Morad, Peshmerge and
Ahmadi, Sina and
Gatti, Lorenzo",
editor = {Bhatia, Archna and
Bouma, Gosse and
Do{\u{g}}ru{\"o}z, A. Seza and
Evang, Kilian and
Garcia, Marcos and
Giouli, Voula and
Han, Lifeng and
Nivre, Joakim and
Rademaker, Alexandre},
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.mwe-1.11",
pages = "70--80",
abstract = "In the growing domain of natural language processing, low-resourced languages like Northern Kurdish remain largely unexplored due to the lack of resources needed to be part of this growth. In particular, the tasks of part-of-speech tagging and tokenization for Northern Kurdish are still insufficiently addressed. In this study, we aim to bridge this gap by evaluating a range of statistical, neural, and fine-tuned-based models specifically tailored for Northern Kurdish. Leveraging limited but valuable datasets, including the Universal Dependency Kurmanji treebank and a novel manually annotated and tokenized gold-standard dataset consisting of 136 sentences (2,937 tokens). We evaluate several POS tagging models and report that the fine-tuned transformer-based model outperforms others, achieving an accuracy of 0.87 and a macro-averaged F1 score of 0.77. Data and models are publicly available under an open license at https://github.com/peshmerge/northern-kurdish-pos-tagging",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morad-etal-2024-part">
<titleInfo>
<title>Part-of-Speech Tagging for Northern Kurdish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peshmerge</namePart>
<namePart type="family">Morad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Gatti</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 Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Archna</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gosse</namePart>
<namePart type="family">Bouma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Voula</namePart>
<namePart type="family">Giouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</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>In the growing domain of natural language processing, low-resourced languages like Northern Kurdish remain largely unexplored due to the lack of resources needed to be part of this growth. In particular, the tasks of part-of-speech tagging and tokenization for Northern Kurdish are still insufficiently addressed. In this study, we aim to bridge this gap by evaluating a range of statistical, neural, and fine-tuned-based models specifically tailored for Northern Kurdish. Leveraging limited but valuable datasets, including the Universal Dependency Kurmanji treebank and a novel manually annotated and tokenized gold-standard dataset consisting of 136 sentences (2,937 tokens). We evaluate several POS tagging models and report that the fine-tuned transformer-based model outperforms others, achieving an accuracy of 0.87 and a macro-averaged F1 score of 0.77. Data and models are publicly available under an open license at https://github.com/peshmerge/northern-kurdish-pos-tagging</abstract>
<identifier type="citekey">morad-etal-2024-part</identifier>
<location>
<url>https://aclanthology.org/2024.mwe-1.11</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>70</start>
<end>80</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Part-of-Speech Tagging for Northern Kurdish
%A Morad, Peshmerge
%A Ahmadi, Sina
%A Gatti, Lorenzo
%Y Bhatia, Archna
%Y Bouma, Gosse
%Y Doğruöz, A. Seza
%Y Evang, Kilian
%Y Garcia, Marcos
%Y Giouli, Voula
%Y Han, Lifeng
%Y Nivre, Joakim
%Y Rademaker, Alexandre
%S Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F morad-etal-2024-part
%X In the growing domain of natural language processing, low-resourced languages like Northern Kurdish remain largely unexplored due to the lack of resources needed to be part of this growth. In particular, the tasks of part-of-speech tagging and tokenization for Northern Kurdish are still insufficiently addressed. In this study, we aim to bridge this gap by evaluating a range of statistical, neural, and fine-tuned-based models specifically tailored for Northern Kurdish. Leveraging limited but valuable datasets, including the Universal Dependency Kurmanji treebank and a novel manually annotated and tokenized gold-standard dataset consisting of 136 sentences (2,937 tokens). We evaluate several POS tagging models and report that the fine-tuned transformer-based model outperforms others, achieving an accuracy of 0.87 and a macro-averaged F1 score of 0.77. Data and models are publicly available under an open license at https://github.com/peshmerge/northern-kurdish-pos-tagging
%U https://aclanthology.org/2024.mwe-1.11
%P 70-80
Markdown (Informal)
[Part-of-Speech Tagging for Northern Kurdish](https://aclanthology.org/2024.mwe-1.11) (Morad et al., MWE-UDW-WS 2024)
ACL
- Peshmerge Morad, Sina Ahmadi, and Lorenzo Gatti. 2024. Part-of-Speech Tagging for Northern Kurdish. In Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024, pages 70–80, Torino, Italia. ELRA and ICCL.