@inproceedings{sakayo-etal-2023-ngambay,
title = "{N}gambay-{F}rench Neural Machine Translation (sba-Fr)",
author = "Sakayo, Toadoum Sari and
Fan, Angela and
Seknewna, Lema Logamou",
editor = "Guti{\'e}rrez, Raquel L{\'a}zaro and
Pareja, Antonio and
Mitkov, Ruslan",
booktitle = "Proceedings of the First Workshop on NLP Tools and Resources for Translation and Interpreting Applications",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.nlp4tia-1.6",
pages = "39--47",
abstract = "In Africa, and the world at large, there is an increasing focus on developing Neural Machine Translation (NMT) systems to overcome language barriers. NMT for Low-resource language is particularly compelling as it involves learning with limited labelled data. However, obtaining a well-aligned parallel corpus for low-resource languages can be challenging. The disparity between the technological advancement of a few global languages and the lack of research on NMT for local languages in Chad is striking. End-to-end NMT trials on low-resource Chad languages have not been attempted. Additionally, there is a dearth of online and well-structured data gathering for research in Natural Language Processing, unlike some African languages. However, a guided approach for data gathering can produce bitext data for many Chadian language translation pairs with well-known languages that have ample data. In this project, we created the first sba-Fr Dataset, which is a corpus of Ngambay-to-French translations, and fine-tuned three pre-trained models using this dataset. Our experiments show that the M2M100 model outperforms other models with high BLEU scores on both original and original+synthetic data. The publicly available bitext dataset can be used for research purposes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakayo-etal-2023-ngambay">
<titleInfo>
<title>Ngambay-French Neural Machine Translation (sba-Fr)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toadoum</namePart>
<namePart type="given">Sari</namePart>
<namePart type="family">Sakayo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lema</namePart>
<namePart type="given">Logamou</namePart>
<namePart type="family">Seknewna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on NLP Tools and Resources for Translation and Interpreting Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="given">Lázaro</namePart>
<namePart type="family">Gutiérrez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Pareja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In Africa, and the world at large, there is an increasing focus on developing Neural Machine Translation (NMT) systems to overcome language barriers. NMT for Low-resource language is particularly compelling as it involves learning with limited labelled data. However, obtaining a well-aligned parallel corpus for low-resource languages can be challenging. The disparity between the technological advancement of a few global languages and the lack of research on NMT for local languages in Chad is striking. End-to-end NMT trials on low-resource Chad languages have not been attempted. Additionally, there is a dearth of online and well-structured data gathering for research in Natural Language Processing, unlike some African languages. However, a guided approach for data gathering can produce bitext data for many Chadian language translation pairs with well-known languages that have ample data. In this project, we created the first sba-Fr Dataset, which is a corpus of Ngambay-to-French translations, and fine-tuned three pre-trained models using this dataset. Our experiments show that the M2M100 model outperforms other models with high BLEU scores on both original and original+synthetic data. The publicly available bitext dataset can be used for research purposes.</abstract>
<identifier type="citekey">sakayo-etal-2023-ngambay</identifier>
<location>
<url>https://aclanthology.org/2023.nlp4tia-1.6</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>39</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ngambay-French Neural Machine Translation (sba-Fr)
%A Sakayo, Toadoum Sari
%A Fan, Angela
%A Seknewna, Lema Logamou
%Y Gutiérrez, Raquel Lázaro
%Y Pareja, Antonio
%Y Mitkov, Ruslan
%S Proceedings of the First Workshop on NLP Tools and Resources for Translation and Interpreting Applications
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F sakayo-etal-2023-ngambay
%X In Africa, and the world at large, there is an increasing focus on developing Neural Machine Translation (NMT) systems to overcome language barriers. NMT for Low-resource language is particularly compelling as it involves learning with limited labelled data. However, obtaining a well-aligned parallel corpus for low-resource languages can be challenging. The disparity between the technological advancement of a few global languages and the lack of research on NMT for local languages in Chad is striking. End-to-end NMT trials on low-resource Chad languages have not been attempted. Additionally, there is a dearth of online and well-structured data gathering for research in Natural Language Processing, unlike some African languages. However, a guided approach for data gathering can produce bitext data for many Chadian language translation pairs with well-known languages that have ample data. In this project, we created the first sba-Fr Dataset, which is a corpus of Ngambay-to-French translations, and fine-tuned three pre-trained models using this dataset. Our experiments show that the M2M100 model outperforms other models with high BLEU scores on both original and original+synthetic data. The publicly available bitext dataset can be used for research purposes.
%U https://aclanthology.org/2023.nlp4tia-1.6
%P 39-47
Markdown (Informal)
[Ngambay-French Neural Machine Translation (sba-Fr)](https://aclanthology.org/2023.nlp4tia-1.6) (Sakayo et al., NLP4TIA-WS 2023)
ACL
- Toadoum Sari Sakayo, Angela Fan, and Lema Logamou Seknewna. 2023. Ngambay-French Neural Machine Translation (sba-Fr). In Proceedings of the First Workshop on NLP Tools and Resources for Translation and Interpreting Applications, pages 39–47, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.