@inproceedings{emezue-etal-2024-igboapi-dataset,
title = "The {I}gbo{API} Dataset: Empowering {I}gbo Language Technologies through Multi-dialectal Enrichment",
author = "Emezue, Chris Chinenye and
Okoh, Ifeoma and
Mbonu, Chinedu Emmanuel and
Chukwuneke, Chiamaka and
Lal, Daisy Monika and
Ezeani, Ignatius and
Rayson, Paul and
Onwuzulike, Ijemma and
Okeke, Chukwuma Onyebuchi and
Nweya, Gerald Okey and
Ogbonna, Bright Ikechukwu and
Oraegbunam, Chukwuebuka Uchenna and
Awo-Ndubuisi, Esther Chidinma and
Osuagwu, Akudo Amarachukwu",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1384",
pages = "15932--15941",
abstract = "The Igbo language is facing a risk of becoming endangered, as indicated by a 2025 UNESCO study. This highlights the need to develop language technologies for Igbo to foster communication, learning and preservation. To create robust, impactful, and widely adopted language technologies for Igbo, it is essential to incorporate the multi-dialectal nature of the language. The primary obstacle in achieving dialectal-aware language technologies is the lack of comprehensive dialectal datasets. In response, we present the IgboAPI dataset, a multi-dialectal Igbo-English dictionary dataset, developed with the aim of enhancing the representation of Igbo dialects. Furthermore, we illustrate the practicality of the IgboAPI dataset through two distinct studies: one focusing on Igbo semantic lexicon and the other on machine translation. In the semantic lexicon project, we successfully establish an initial Igbo semantic lexicon for the Igbo semantic tagger, while in the machine translation study, we demonstrate that by finetuning existing machine translation systems using the IgboAPI dataset, we significantly improve their ability to handle dialectal variations in sentences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="emezue-etal-2024-igboapi-dataset">
<titleInfo>
<title>The IgboAPI Dataset: Empowering Igbo Language Technologies through Multi-dialectal Enrichment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="given">Chinenye</namePart>
<namePart type="family">Emezue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ifeoma</namePart>
<namePart type="family">Okoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chinedu</namePart>
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Mbonu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiamaka</namePart>
<namePart type="family">Chukwuneke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisy</namePart>
<namePart type="given">Monika</namePart>
<namePart type="family">Lal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ignatius</namePart>
<namePart type="family">Ezeani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ijemma</namePart>
<namePart type="family">Onwuzulike</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chukwuma</namePart>
<namePart type="given">Onyebuchi</namePart>
<namePart type="family">Okeke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerald</namePart>
<namePart type="given">Okey</namePart>
<namePart type="family">Nweya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bright</namePart>
<namePart type="given">Ikechukwu</namePart>
<namePart type="family">Ogbonna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chukwuebuka</namePart>
<namePart type="given">Uchenna</namePart>
<namePart type="family">Oraegbunam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esther</namePart>
<namePart type="given">Chidinma</namePart>
<namePart type="family">Awo-Ndubuisi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akudo</namePart>
<namePart type="given">Amarachukwu</namePart>
<namePart type="family">Osuagwu</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>The Igbo language is facing a risk of becoming endangered, as indicated by a 2025 UNESCO study. This highlights the need to develop language technologies for Igbo to foster communication, learning and preservation. To create robust, impactful, and widely adopted language technologies for Igbo, it is essential to incorporate the multi-dialectal nature of the language. The primary obstacle in achieving dialectal-aware language technologies is the lack of comprehensive dialectal datasets. In response, we present the IgboAPI dataset, a multi-dialectal Igbo-English dictionary dataset, developed with the aim of enhancing the representation of Igbo dialects. Furthermore, we illustrate the practicality of the IgboAPI dataset through two distinct studies: one focusing on Igbo semantic lexicon and the other on machine translation. In the semantic lexicon project, we successfully establish an initial Igbo semantic lexicon for the Igbo semantic tagger, while in the machine translation study, we demonstrate that by finetuning existing machine translation systems using the IgboAPI dataset, we significantly improve their ability to handle dialectal variations in sentences.</abstract>
<identifier type="citekey">emezue-etal-2024-igboapi-dataset</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1384</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15932</start>
<end>15941</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The IgboAPI Dataset: Empowering Igbo Language Technologies through Multi-dialectal Enrichment
%A Emezue, Chris Chinenye
%A Okoh, Ifeoma
%A Mbonu, Chinedu Emmanuel
%A Chukwuneke, Chiamaka
%A Lal, Daisy Monika
%A Ezeani, Ignatius
%A Rayson, Paul
%A Onwuzulike, Ijemma
%A Okeke, Chukwuma Onyebuchi
%A Nweya, Gerald Okey
%A Ogbonna, Bright Ikechukwu
%A Oraegbunam, Chukwuebuka Uchenna
%A Awo-Ndubuisi, Esther Chidinma
%A Osuagwu, Akudo Amarachukwu
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F emezue-etal-2024-igboapi-dataset
%X The Igbo language is facing a risk of becoming endangered, as indicated by a 2025 UNESCO study. This highlights the need to develop language technologies for Igbo to foster communication, learning and preservation. To create robust, impactful, and widely adopted language technologies for Igbo, it is essential to incorporate the multi-dialectal nature of the language. The primary obstacle in achieving dialectal-aware language technologies is the lack of comprehensive dialectal datasets. In response, we present the IgboAPI dataset, a multi-dialectal Igbo-English dictionary dataset, developed with the aim of enhancing the representation of Igbo dialects. Furthermore, we illustrate the practicality of the IgboAPI dataset through two distinct studies: one focusing on Igbo semantic lexicon and the other on machine translation. In the semantic lexicon project, we successfully establish an initial Igbo semantic lexicon for the Igbo semantic tagger, while in the machine translation study, we demonstrate that by finetuning existing machine translation systems using the IgboAPI dataset, we significantly improve their ability to handle dialectal variations in sentences.
%U https://aclanthology.org/2024.lrec-main.1384
%P 15932-15941
Markdown (Informal)
[The IgboAPI Dataset: Empowering Igbo Language Technologies through Multi-dialectal Enrichment](https://aclanthology.org/2024.lrec-main.1384) (Emezue et al., LREC-COLING 2024)
ACL
- Chris Chinenye Emezue, Ifeoma Okoh, Chinedu Emmanuel Mbonu, Chiamaka Chukwuneke, Daisy Monika Lal, Ignatius Ezeani, Paul Rayson, Ijemma Onwuzulike, Chukwuma Onyebuchi Okeke, Gerald Okey Nweya, Bright Ikechukwu Ogbonna, Chukwuebuka Uchenna Oraegbunam, Esther Chidinma Awo-Ndubuisi, and Akudo Amarachukwu Osuagwu. 2024. The IgboAPI Dataset: Empowering Igbo Language Technologies through Multi-dialectal Enrichment. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15932–15941, Torino, Italia. ELRA and ICCL.