@inproceedings{akinfaderin-2020-hausamt,
title = "{H}ausa{MT} v1.0: Towards {E}nglish{--}{H}ausa Neural Machine Translation",
author = "Akinfaderin, Adewale",
editor = "Cunha, Rossana and
Shaikh, Samira and
Varis, Erika and
Georgi, Ryan and
Tsai, Alicia and
Anastasopoulos, Antonios and
Chandu, Khyathi Raghavi",
booktitle = "Proceedings of the Fourth Widening Natural Language Processing Workshop",
month = jul,
year = "2020",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.winlp-1.38",
doi = "10.18653/v1/2020.winlp-1.38",
pages = "144--147",
abstract = "Neural Machine Translation (NMT) for low-resource languages suffers from low performance because of the lack of large amounts of parallel data and language diversity. To contribute to ameliorating this problem, we built a baseline model for English{--}Hausa machine translation, which is considered a task for low{--}resource language. The Hausa language is the second largest Afro{--}Asiatic language in the world after Arabic and it is the third largest language for trading across a larger swath of West Africa countries, after English and French. In this paper, we curated different datasets containing Hausa{--}English parallel corpus for our translation. We trained baseline models and evaluated the performance of our models using the Recurrent and Transformer encoder{--}decoder architecture with two tokenization approaches: standard word{--}level tokenization and Byte Pair Encoding (BPE) subword tokenization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akinfaderin-2020-hausamt">
<titleInfo>
<title>HausaMT v1.0: Towards English–Hausa Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adewale</namePart>
<namePart type="family">Akinfaderin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Widening Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rossana</namePart>
<namePart type="family">Cunha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erika</namePart>
<namePart type="family">Varis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Georgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Machine Translation (NMT) for low-resource languages suffers from low performance because of the lack of large amounts of parallel data and language diversity. To contribute to ameliorating this problem, we built a baseline model for English–Hausa machine translation, which is considered a task for low–resource language. The Hausa language is the second largest Afro–Asiatic language in the world after Arabic and it is the third largest language for trading across a larger swath of West Africa countries, after English and French. In this paper, we curated different datasets containing Hausa–English parallel corpus for our translation. We trained baseline models and evaluated the performance of our models using the Recurrent and Transformer encoder–decoder architecture with two tokenization approaches: standard word–level tokenization and Byte Pair Encoding (BPE) subword tokenization.</abstract>
<identifier type="citekey">akinfaderin-2020-hausamt</identifier>
<identifier type="doi">10.18653/v1/2020.winlp-1.38</identifier>
<location>
<url>https://aclanthology.org/2020.winlp-1.38</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>144</start>
<end>147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HausaMT v1.0: Towards English–Hausa Neural Machine Translation
%A Akinfaderin, Adewale
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Varis, Erika
%Y Georgi, Ryan
%Y Tsai, Alicia
%Y Anastasopoulos, Antonios
%Y Chandu, Khyathi Raghavi
%S Proceedings of the Fourth Widening Natural Language Processing Workshop
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F akinfaderin-2020-hausamt
%X Neural Machine Translation (NMT) for low-resource languages suffers from low performance because of the lack of large amounts of parallel data and language diversity. To contribute to ameliorating this problem, we built a baseline model for English–Hausa machine translation, which is considered a task for low–resource language. The Hausa language is the second largest Afro–Asiatic language in the world after Arabic and it is the third largest language for trading across a larger swath of West Africa countries, after English and French. In this paper, we curated different datasets containing Hausa–English parallel corpus for our translation. We trained baseline models and evaluated the performance of our models using the Recurrent and Transformer encoder–decoder architecture with two tokenization approaches: standard word–level tokenization and Byte Pair Encoding (BPE) subword tokenization.
%R 10.18653/v1/2020.winlp-1.38
%U https://aclanthology.org/2020.winlp-1.38
%U https://doi.org/10.18653/v1/2020.winlp-1.38
%P 144-147
Markdown (Informal)
[HausaMT v1.0: Towards English–Hausa Neural Machine Translation](https://aclanthology.org/2020.winlp-1.38) (Akinfaderin, WiNLP 2020)
ACL