@inproceedings{tonja-etal-2024-ethiomt,
title = "{E}thio{MT}: Parallel Corpus for Low-resource {E}thiopian Languages",
author = "Tonja, Atnafu Lambebo and
Kolesnikova, Olga and
Gelbukh, Alexander and
Kalita, Jugal",
editor = "Mabuya, Rooweither and
Matfunjwa, Muzi and
Setaka, Mmasibidi and
van Zaanen, Menno",
booktitle = "Proceedings of the Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.rail-1.12",
pages = "107--114",
abstract = "Recent research in natural language processing (NLP) has achieved impressive performance in tasks such as machine translation (MT), news classification, and question-answering in high-resource languages. However, the performance of MT leaves much to be desired for low-resource languages. This is due to the smaller size of available parallel corpora in these languages, if such corpora are available at all. NLP in Ethiopian languages suffers from the same issues due to the unavailability of publicly accessible datasets for NLP tasks, including MT. To help the research community and foster research for Ethiopian languages, we introduce EthioMT {--} a new parallel corpus for 15 languages. We also create a new benchmark by collecting a dataset for better-researched languages in Ethiopia. We evaluate the newly collected corpus and the benchmark dataset for 23 Ethiopian languages using transformer and fine-tuning approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tonja-etal-2024-ethiomt">
<titleInfo>
<title>EthioMT: Parallel Corpus for Low-resource Ethiopian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atnafu</namePart>
<namePart type="given">Lambebo</namePart>
<namePart type="family">Tonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kolesnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gelbukh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jugal</namePart>
<namePart type="family">Kalita</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 Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muzi</namePart>
<namePart type="family">Matfunjwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mmasibidi</namePart>
<namePart type="family">Setaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menno</namePart>
<namePart type="family">van Zaanen</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>Recent research in natural language processing (NLP) has achieved impressive performance in tasks such as machine translation (MT), news classification, and question-answering in high-resource languages. However, the performance of MT leaves much to be desired for low-resource languages. This is due to the smaller size of available parallel corpora in these languages, if such corpora are available at all. NLP in Ethiopian languages suffers from the same issues due to the unavailability of publicly accessible datasets for NLP tasks, including MT. To help the research community and foster research for Ethiopian languages, we introduce EthioMT – a new parallel corpus for 15 languages. We also create a new benchmark by collecting a dataset for better-researched languages in Ethiopia. We evaluate the newly collected corpus and the benchmark dataset for 23 Ethiopian languages using transformer and fine-tuning approaches.</abstract>
<identifier type="citekey">tonja-etal-2024-ethiomt</identifier>
<location>
<url>https://aclanthology.org/2024.rail-1.12</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>107</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EthioMT: Parallel Corpus for Low-resource Ethiopian Languages
%A Tonja, Atnafu Lambebo
%A Kolesnikova, Olga
%A Gelbukh, Alexander
%A Kalita, Jugal
%Y Mabuya, Rooweither
%Y Matfunjwa, Muzi
%Y Setaka, Mmasibidi
%Y van Zaanen, Menno
%S Proceedings of the Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F tonja-etal-2024-ethiomt
%X Recent research in natural language processing (NLP) has achieved impressive performance in tasks such as machine translation (MT), news classification, and question-answering in high-resource languages. However, the performance of MT leaves much to be desired for low-resource languages. This is due to the smaller size of available parallel corpora in these languages, if such corpora are available at all. NLP in Ethiopian languages suffers from the same issues due to the unavailability of publicly accessible datasets for NLP tasks, including MT. To help the research community and foster research for Ethiopian languages, we introduce EthioMT – a new parallel corpus for 15 languages. We also create a new benchmark by collecting a dataset for better-researched languages in Ethiopia. We evaluate the newly collected corpus and the benchmark dataset for 23 Ethiopian languages using transformer and fine-tuning approaches.
%U https://aclanthology.org/2024.rail-1.12
%P 107-114
Markdown (Informal)
[EthioMT: Parallel Corpus for Low-resource Ethiopian Languages](https://aclanthology.org/2024.rail-1.12) (Tonja et al., RAIL-WS 2024)
ACL