@inproceedings{ali-etal-2024-building,
title = "Building Resources for Emakhuwa: Machine Translation and News Classification Benchmarks",
author = "Ali, Felermino D. M. A. and
Lopes Cardoso, Henrique and
Sousa-Silva, Rui",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.824/",
doi = "10.18653/v1/2024.emnlp-main.824",
pages = "14842--14857",
abstract = "This paper introduces a comprehensive collection of NLP resources for Emakhuwa, Mozambique`s most widely spoken language. The resources include the first manually translated news bitext corpus between Portuguese and Emakhuwa, news topic classification datasets, and monolingual data. We detail the process and challenges of acquiring this data and present benchmark results for machine translation and news topic classification tasks. Our evaluation examines the impact of different data types{---}originally clean text, post-corrected OCR, and back-translated data{---}and the effects of fine-tuning from pre-trained models, including those focused on African languages.Our benchmarks demonstrate good performance in news topic classification and promising results in machine translation. We fine-tuned multilingual encoder-decoder models using real and synthetic data and evaluated them on our test set and the FLORES evaluation sets. The results highlight the importance of incorporating more data and potential for future improvements.All models, code, and datasets are available in the \url{https://huggingface.co/LIACC} repository under the CC BY 4.0 license."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ali-etal-2024-building">
<titleInfo>
<title>Building Resources for Emakhuwa: Machine Translation and News Classification Benchmarks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felermino</namePart>
<namePart type="given">D</namePart>
<namePart type="given">M</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrique</namePart>
<namePart type="family">Lopes Cardoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Sousa-Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a comprehensive collection of NLP resources for Emakhuwa, Mozambique‘s most widely spoken language. The resources include the first manually translated news bitext corpus between Portuguese and Emakhuwa, news topic classification datasets, and monolingual data. We detail the process and challenges of acquiring this data and present benchmark results for machine translation and news topic classification tasks. Our evaluation examines the impact of different data types—originally clean text, post-corrected OCR, and back-translated data—and the effects of fine-tuning from pre-trained models, including those focused on African languages.Our benchmarks demonstrate good performance in news topic classification and promising results in machine translation. We fine-tuned multilingual encoder-decoder models using real and synthetic data and evaluated them on our test set and the FLORES evaluation sets. The results highlight the importance of incorporating more data and potential for future improvements.All models, code, and datasets are available in the https://huggingface.co/LIACC repository under the CC BY 4.0 license.</abstract>
<identifier type="citekey">ali-etal-2024-building</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.824</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.824/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>14842</start>
<end>14857</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Resources for Emakhuwa: Machine Translation and News Classification Benchmarks
%A Ali, Felermino D. M. A.
%A Lopes Cardoso, Henrique
%A Sousa-Silva, Rui
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F ali-etal-2024-building
%X This paper introduces a comprehensive collection of NLP resources for Emakhuwa, Mozambique‘s most widely spoken language. The resources include the first manually translated news bitext corpus between Portuguese and Emakhuwa, news topic classification datasets, and monolingual data. We detail the process and challenges of acquiring this data and present benchmark results for machine translation and news topic classification tasks. Our evaluation examines the impact of different data types—originally clean text, post-corrected OCR, and back-translated data—and the effects of fine-tuning from pre-trained models, including those focused on African languages.Our benchmarks demonstrate good performance in news topic classification and promising results in machine translation. We fine-tuned multilingual encoder-decoder models using real and synthetic data and evaluated them on our test set and the FLORES evaluation sets. The results highlight the importance of incorporating more data and potential for future improvements.All models, code, and datasets are available in the https://huggingface.co/LIACC repository under the CC BY 4.0 license.
%R 10.18653/v1/2024.emnlp-main.824
%U https://aclanthology.org/2024.emnlp-main.824/
%U https://doi.org/10.18653/v1/2024.emnlp-main.824
%P 14842-14857
Markdown (Informal)
[Building Resources for Emakhuwa: Machine Translation and News Classification Benchmarks](https://aclanthology.org/2024.emnlp-main.824/) (Ali et al., EMNLP 2024)
ACL