@inproceedings{marivate-etal-2020-investigating,
title = "Investigating an Approach for Low Resource Language Dataset Creation, Curation and Classification: Setswana and Sepedi",
author = "Marivate, Vukosi and
Sefara, Tshephisho and
Chabalala, Vongani and
Makhaya, Keamogetswe and
Mokgonyane, Tumisho and
Mokoena, Rethabile and
Modupe, Abiodun",
editor = "Mabuya, Rooweither and
Ramukhadi, Phathutshedzo and
Setaka, Mmasibidi and
Wagner, Valencia and
van Zaanen, Menno",
booktitle = "Proceedings of the first workshop on Resources for African Indigenous Languages",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.rail-1.3",
pages = "15--20",
abstract = "The recent advances in Natural Language Processing have only been a boon for well represented languages, negating research in lesser known global languages. This is in part due to the availability of curated data and research resources. One of the current challenges concerning low-resourced languages are clear guidelines on the collection, curation and preparation of datasets for different use-cases. In this work, we take on the task of creating two datasets that are focused on news headlines (i.e short text) for Setswana and Sepedi and the creation of a news topic classification task from these datasets. In this study, we document our work, propose baselines for classification, and investigate an approach on data augmentation better suited to low-resourced languages in order to improve the performance of the classifiers.",
language = "English",
ISBN = "979-10-95546-60-3",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marivate-etal-2020-investigating">
<titleInfo>
<title>Investigating an Approach for Low Resource Language Dataset Creation, Curation and Classification: Setswana and Sepedi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vukosi</namePart>
<namePart type="family">Marivate</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tshephisho</namePart>
<namePart type="family">Sefara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vongani</namePart>
<namePart type="family">Chabalala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keamogetswe</namePart>
<namePart type="family">Makhaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tumisho</namePart>
<namePart type="family">Mokgonyane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rethabile</namePart>
<namePart type="family">Mokoena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abiodun</namePart>
<namePart type="family">Modupe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the first workshop on Resources for African Indigenous Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phathutshedzo</namePart>
<namePart type="family">Ramukhadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mmasibidi</namePart>
<namePart type="family">Setaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valencia</namePart>
<namePart type="family">Wagner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menno</namePart>
<namePart type="family">van Zaanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-60-3</identifier>
</relatedItem>
<abstract>The recent advances in Natural Language Processing have only been a boon for well represented languages, negating research in lesser known global languages. This is in part due to the availability of curated data and research resources. One of the current challenges concerning low-resourced languages are clear guidelines on the collection, curation and preparation of datasets for different use-cases. In this work, we take on the task of creating two datasets that are focused on news headlines (i.e short text) for Setswana and Sepedi and the creation of a news topic classification task from these datasets. In this study, we document our work, propose baselines for classification, and investigate an approach on data augmentation better suited to low-resourced languages in order to improve the performance of the classifiers.</abstract>
<identifier type="citekey">marivate-etal-2020-investigating</identifier>
<location>
<url>https://aclanthology.org/2020.rail-1.3</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>15</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating an Approach for Low Resource Language Dataset Creation, Curation and Classification: Setswana and Sepedi
%A Marivate, Vukosi
%A Sefara, Tshephisho
%A Chabalala, Vongani
%A Makhaya, Keamogetswe
%A Mokgonyane, Tumisho
%A Mokoena, Rethabile
%A Modupe, Abiodun
%Y Mabuya, Rooweither
%Y Ramukhadi, Phathutshedzo
%Y Setaka, Mmasibidi
%Y Wagner, Valencia
%Y van Zaanen, Menno
%S Proceedings of the first workshop on Resources for African Indigenous Languages
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-60-3
%G English
%F marivate-etal-2020-investigating
%X The recent advances in Natural Language Processing have only been a boon for well represented languages, negating research in lesser known global languages. This is in part due to the availability of curated data and research resources. One of the current challenges concerning low-resourced languages are clear guidelines on the collection, curation and preparation of datasets for different use-cases. In this work, we take on the task of creating two datasets that are focused on news headlines (i.e short text) for Setswana and Sepedi and the creation of a news topic classification task from these datasets. In this study, we document our work, propose baselines for classification, and investigate an approach on data augmentation better suited to low-resourced languages in order to improve the performance of the classifiers.
%U https://aclanthology.org/2020.rail-1.3
%P 15-20
Markdown (Informal)
[Investigating an Approach for Low Resource Language Dataset Creation, Curation and Classification: Setswana and Sepedi](https://aclanthology.org/2020.rail-1.3) (Marivate et al., RAIL 2020)
ACL
- Vukosi Marivate, Tshephisho Sefara, Vongani Chabalala, Keamogetswe Makhaya, Tumisho Mokgonyane, Rethabile Mokoena, and Abiodun Modupe. 2020. Investigating an Approach for Low Resource Language Dataset Creation, Curation and Classification: Setswana and Sepedi. In Proceedings of the first workshop on Resources for African Indigenous Languages, pages 15–20, Marseille, France. European Language Resources Association (ELRA).