@inproceedings{cisse-sadat-2023-automatic,
title = "Automatic Spell Checker and Correction for Under-represented Spoken Languages: Case Study on {W}olof",
author = "Ciss{\'e}, Thierno Ibrahima and
Sadat, Fatiha",
editor = "Mabuya, Rooweither and
Mthobela, Don and
Setaka, Mmasibidi and
Van Zaanen, Menno",
booktitle = "Proceedings of the Fourth workshop on Resources for African Indigenous Languages (RAIL 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.rail-1.1",
doi = "10.18653/v1/2023.rail-1.1",
pages = "1--10",
abstract = "This paper presents a spell checker and correction tool specifically designed for Wolof, an under-represented spoken language in Africa. The proposed spell checker leverages a combination of a trie data structure, dynamic programming, and the weighted Levenshtein distance to generate suggestions for misspelled words. We created novel linguistic resources for Wolof, such as a lexicon and a corpus of misspelled words, using a semi-automatic approach that combines manual and automatic annotation methods. Despite the limited data available for the Wolof language, the spell checker{'}s performance showed a predictive accuracy of 98.31{\%} and a suggestion accuracy of 93.33{\%}.Our primary focus remains the revitalization and preservation of Wolof as an Indigenous and spoken language in Africa, providing our efforts to develop novel linguistic resources. This work represents a valuable contribution to the growth of computational tools and resources for the Wolof language and provides a strong foundation for future studies in the automatic spell checking and correction field.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cisse-sadat-2023-automatic">
<titleInfo>
<title>Automatic Spell Checker and Correction for Under-represented Spoken Languages: Case Study on Wolof</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thierno</namePart>
<namePart type="given">Ibrahima</namePart>
<namePart type="family">Cissé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatiha</namePart>
<namePart type="family">Sadat</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 Fourth workshop on Resources for African Indigenous Languages (RAIL 2023)</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">Don</namePart>
<namePart type="family">Mthobela</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">Menno</namePart>
<namePart type="family">Van Zaanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a spell checker and correction tool specifically designed for Wolof, an under-represented spoken language in Africa. The proposed spell checker leverages a combination of a trie data structure, dynamic programming, and the weighted Levenshtein distance to generate suggestions for misspelled words. We created novel linguistic resources for Wolof, such as a lexicon and a corpus of misspelled words, using a semi-automatic approach that combines manual and automatic annotation methods. Despite the limited data available for the Wolof language, the spell checker’s performance showed a predictive accuracy of 98.31% and a suggestion accuracy of 93.33%.Our primary focus remains the revitalization and preservation of Wolof as an Indigenous and spoken language in Africa, providing our efforts to develop novel linguistic resources. This work represents a valuable contribution to the growth of computational tools and resources for the Wolof language and provides a strong foundation for future studies in the automatic spell checking and correction field.</abstract>
<identifier type="citekey">cisse-sadat-2023-automatic</identifier>
<identifier type="doi">10.18653/v1/2023.rail-1.1</identifier>
<location>
<url>https://aclanthology.org/2023.rail-1.1</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Spell Checker and Correction for Under-represented Spoken Languages: Case Study on Wolof
%A Cissé, Thierno Ibrahima
%A Sadat, Fatiha
%Y Mabuya, Rooweither
%Y Mthobela, Don
%Y Setaka, Mmasibidi
%Y Van Zaanen, Menno
%S Proceedings of the Fourth workshop on Resources for African Indigenous Languages (RAIL 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F cisse-sadat-2023-automatic
%X This paper presents a spell checker and correction tool specifically designed for Wolof, an under-represented spoken language in Africa. The proposed spell checker leverages a combination of a trie data structure, dynamic programming, and the weighted Levenshtein distance to generate suggestions for misspelled words. We created novel linguistic resources for Wolof, such as a lexicon and a corpus of misspelled words, using a semi-automatic approach that combines manual and automatic annotation methods. Despite the limited data available for the Wolof language, the spell checker’s performance showed a predictive accuracy of 98.31% and a suggestion accuracy of 93.33%.Our primary focus remains the revitalization and preservation of Wolof as an Indigenous and spoken language in Africa, providing our efforts to develop novel linguistic resources. This work represents a valuable contribution to the growth of computational tools and resources for the Wolof language and provides a strong foundation for future studies in the automatic spell checking and correction field.
%R 10.18653/v1/2023.rail-1.1
%U https://aclanthology.org/2023.rail-1.1
%U https://doi.org/10.18653/v1/2023.rail-1.1
%P 1-10
Markdown (Informal)
[Automatic Spell Checker and Correction for Under-represented Spoken Languages: Case Study on Wolof](https://aclanthology.org/2023.rail-1.1) (Cissé & Sadat, RAIL 2023)
ACL