@inproceedings{akinade-etal-2023-varepsilon,
title = "Varepsilon k{\'u} mask: Integrating {Y}or{\`u}b{\'a} cultural greetings into machine translation",
author = "Akinade, Idris and
Alabi, Jesujoba and
Adelani, David and
Odoje, Clement and
Klakow, Dietrich",
editor = "Dev, Sunipa and
Prabhakaran, Vinodkumar and
Adelani, David and
Hovy, Dirk and
Benotti, Luciana",
booktitle = "Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.c3nlp-1.1",
doi = "10.18653/v1/2023.c3nlp-1.1",
pages = "1--7",
abstract = "This paper investigates the performance of massively multilingual neural machine translation (NMT) systems in translating Yor{\`u}b{\'a} greetings (k{\'u} mask), which are a big part of Yor{\`u}b{\'a} language and culture, into English. To evaluate these models, we present IkiniYor{\`u}b{\'a}, a Yor{\`u}b{\'a}-English translation dataset containing some Yor{\`u}b{\'a} greetings, and sample use cases. We analysed the performance of different multilingual NMT systems including Google and NLLB and show that these models struggle to accurately translate Yor{\`u}b{\'a} greetings into English. In addition, we trained a Yor{\`u}b{\'a}-English model by fine-tuning an existing NMT model on the training split of IkiniYor{\`u}b{\'a} and this achieved better performance when compared to the pre-trained multilingual NMT models, although they were trained on a large volume of data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akinade-etal-2023-varepsilon">
<titleInfo>
<title>Varepsilon kú mask: Integrating Yorùbá cultural greetings into machine translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Idris</namePart>
<namePart type="family">Akinade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clement</namePart>
<namePart type="family">Odoje</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</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 First Workshop on Cross-Cultural Considerations in NLP (C3NLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinodkumar</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luciana</namePart>
<namePart type="family">Benotti</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 investigates the performance of massively multilingual neural machine translation (NMT) systems in translating Yorùbá greetings (kú mask), which are a big part of Yorùbá language and culture, into English. To evaluate these models, we present IkiniYorùbá, a Yorùbá-English translation dataset containing some Yorùbá greetings, and sample use cases. We analysed the performance of different multilingual NMT systems including Google and NLLB and show that these models struggle to accurately translate Yorùbá greetings into English. In addition, we trained a Yorùbá-English model by fine-tuning an existing NMT model on the training split of IkiniYorùbá and this achieved better performance when compared to the pre-trained multilingual NMT models, although they were trained on a large volume of data.</abstract>
<identifier type="citekey">akinade-etal-2023-varepsilon</identifier>
<identifier type="doi">10.18653/v1/2023.c3nlp-1.1</identifier>
<location>
<url>https://aclanthology.org/2023.c3nlp-1.1</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1</start>
<end>7</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Varepsilon kú mask: Integrating Yorùbá cultural greetings into machine translation
%A Akinade, Idris
%A Alabi, Jesujoba
%A Adelani, David
%A Odoje, Clement
%A Klakow, Dietrich
%Y Dev, Sunipa
%Y Prabhakaran, Vinodkumar
%Y Adelani, David
%Y Hovy, Dirk
%Y Benotti, Luciana
%S Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F akinade-etal-2023-varepsilon
%X This paper investigates the performance of massively multilingual neural machine translation (NMT) systems in translating Yorùbá greetings (kú mask), which are a big part of Yorùbá language and culture, into English. To evaluate these models, we present IkiniYorùbá, a Yorùbá-English translation dataset containing some Yorùbá greetings, and sample use cases. We analysed the performance of different multilingual NMT systems including Google and NLLB and show that these models struggle to accurately translate Yorùbá greetings into English. In addition, we trained a Yorùbá-English model by fine-tuning an existing NMT model on the training split of IkiniYorùbá and this achieved better performance when compared to the pre-trained multilingual NMT models, although they were trained on a large volume of data.
%R 10.18653/v1/2023.c3nlp-1.1
%U https://aclanthology.org/2023.c3nlp-1.1
%U https://doi.org/10.18653/v1/2023.c3nlp-1.1
%P 1-7
Markdown (Informal)
[Varepsilon kú mask: Integrating Yorùbá cultural greetings into machine translation](https://aclanthology.org/2023.c3nlp-1.1) (Akinade et al., C3NLP 2023)
ACL