@inproceedings{sayed-etal-2025-usage,
title = "On the Usage of Semantics, Syntax, and Morphology for Noun Classification in {I}si{Z}ulu",
author = "Sayed, Imaan and
Mahlaza, Zola and
van der Leek, Alexander and
Mopp, Jonathan and
Keet, C. Maria",
editor = "Holdt, {\v{S}}pela Arhar and
Ilinykh, Nikolai and
Scalvini, Barbara and
Bruton, Micaella and
Debess, Iben Nyholm and
Tudor, Crina Madalina",
booktitle = "Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library, Estonia",
url = "https://aclanthology.org/2025.resourceful-1.23/",
pages = "96--105",
ISBN = "978-9908-53-121-2",
abstract = "There is limited work aimed at solving the core task of noun classification for Nguni languages. The task focuses on identifying the semantic categorisation of each noun and plays a crucial role in the ability to form semantically and morphologically valid sentences. The work by Byamugisha (2022) was the first to tackle the problem for a related, but non-Nguni, language. While there have been efforts to replicate it for a Nguni language, there has been no effort focused on comparing the technique used in the original work vs. contemporary neural methods or a number of traditional machine learning classification techniques that do not rely on human-guided knowledge to the same extent. We reproduce Byamugisha (2022){'}s work with different configurations to account for differences in access to datasets and resources, compare the approach with a pre-trained transformer-based model, and traditional machine learning models that relyon less human-guided knowledge. The newly created data-driven models outperform the knowledge-infused models, with the best performing models achieving an F1 score of 0.97."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sayed-etal-2025-usage">
<titleInfo>
<title>On the Usage of Semantics, Syntax, and Morphology for Noun Classification in IsiZulu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Imaan</namePart>
<namePart type="family">Sayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zola</namePart>
<namePart type="family">Mahlaza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">van der Leek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Mopp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Keet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Špela</namePart>
<namePart type="given">Arhar</namePart>
<namePart type="family">Holdt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micaella</namePart>
<namePart type="family">Bruton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</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">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Crina</namePart>
<namePart type="given">Madalina</namePart>
<namePart type="family">Tudor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library, Estonia</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-121-2</identifier>
</relatedItem>
<abstract>There is limited work aimed at solving the core task of noun classification for Nguni languages. The task focuses on identifying the semantic categorisation of each noun and plays a crucial role in the ability to form semantically and morphologically valid sentences. The work by Byamugisha (2022) was the first to tackle the problem for a related, but non-Nguni, language. While there have been efforts to replicate it for a Nguni language, there has been no effort focused on comparing the technique used in the original work vs. contemporary neural methods or a number of traditional machine learning classification techniques that do not rely on human-guided knowledge to the same extent. We reproduce Byamugisha (2022)’s work with different configurations to account for differences in access to datasets and resources, compare the approach with a pre-trained transformer-based model, and traditional machine learning models that relyon less human-guided knowledge. The newly created data-driven models outperform the knowledge-infused models, with the best performing models achieving an F1 score of 0.97.</abstract>
<identifier type="citekey">sayed-etal-2025-usage</identifier>
<location>
<url>https://aclanthology.org/2025.resourceful-1.23/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>96</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Usage of Semantics, Syntax, and Morphology for Noun Classification in IsiZulu
%A Sayed, Imaan
%A Mahlaza, Zola
%A van der Leek, Alexander
%A Mopp, Jonathan
%A Keet, C. Maria
%Y Holdt, Špela Arhar
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Bruton, Micaella
%Y Debess, Iben Nyholm
%Y Tudor, Crina Madalina
%S Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)
%D 2025
%8 March
%I University of Tartu Library, Estonia
%C Tallinn, Estonia
%@ 978-9908-53-121-2
%F sayed-etal-2025-usage
%X There is limited work aimed at solving the core task of noun classification for Nguni languages. The task focuses on identifying the semantic categorisation of each noun and plays a crucial role in the ability to form semantically and morphologically valid sentences. The work by Byamugisha (2022) was the first to tackle the problem for a related, but non-Nguni, language. While there have been efforts to replicate it for a Nguni language, there has been no effort focused on comparing the technique used in the original work vs. contemporary neural methods or a number of traditional machine learning classification techniques that do not rely on human-guided knowledge to the same extent. We reproduce Byamugisha (2022)’s work with different configurations to account for differences in access to datasets and resources, compare the approach with a pre-trained transformer-based model, and traditional machine learning models that relyon less human-guided knowledge. The newly created data-driven models outperform the knowledge-infused models, with the best performing models achieving an F1 score of 0.97.
%U https://aclanthology.org/2025.resourceful-1.23/
%P 96-105
Markdown (Informal)
[On the Usage of Semantics, Syntax, and Morphology for Noun Classification in IsiZulu](https://aclanthology.org/2025.resourceful-1.23/) (Sayed et al., RESOURCEFUL 2025)
ACL
- Imaan Sayed, Zola Mahlaza, Alexander van der Leek, Jonathan Mopp, and C. Maria Keet. 2025. On the Usage of Semantics, Syntax, and Morphology for Noun Classification in IsiZulu. In Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025), pages 96–105, Tallinn, Estonia. University of Tartu Library, Estonia.