@inproceedings{atnafu-lambebo-etal-2023-first,
title = "First Attempt at Building Parallel Corpora for Machine Translation of {N}ortheast {I}ndia{'}s Very Low-Resource Languages",
author = "Atnafu Lambebo, Tonja and
Melkamu, Mersha and
Ananya, Kalita and
Olga, Kolesnikova and
Jugal, Kalita",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.49",
pages = "534--539",
abstract = "This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India. It also presents the results of initial translation efforts in these languages. It creates the first-ever parallel corpora for these languages and provides initial benchmark neural machine translation results for these languages. We intend to extend these corpora to include a large number of low-resource Indian languages and integrate the effort with our prior work with African and American-Indian languages to create corpora covering a large number of languages from across the world.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atnafu-lambebo-etal-2023-first">
<titleInfo>
<title>First Attempt at Building Parallel Corpora for Machine Translation of Northeast India’s Very Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tonja</namePart>
<namePart type="family">Atnafu Lambebo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mersha</namePart>
<namePart type="family">Melkamu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalita</namePart>
<namePart type="family">Ananya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kolesnikova</namePart>
<namePart type="family">Olga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalita</namePart>
<namePart type="family">Jugal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India. It also presents the results of initial translation efforts in these languages. It creates the first-ever parallel corpora for these languages and provides initial benchmark neural machine translation results for these languages. We intend to extend these corpora to include a large number of low-resource Indian languages and integrate the effort with our prior work with African and American-Indian languages to create corpora covering a large number of languages from across the world.</abstract>
<identifier type="citekey">atnafu-lambebo-etal-2023-first</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.49</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>534</start>
<end>539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T First Attempt at Building Parallel Corpora for Machine Translation of Northeast India’s Very Low-Resource Languages
%A Atnafu Lambebo, Tonja
%A Melkamu, Mersha
%A Ananya, Kalita
%A Olga, Kolesnikova
%A Jugal, Kalita
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F atnafu-lambebo-etal-2023-first
%X This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India. It also presents the results of initial translation efforts in these languages. It creates the first-ever parallel corpora for these languages and provides initial benchmark neural machine translation results for these languages. We intend to extend these corpora to include a large number of low-resource Indian languages and integrate the effort with our prior work with African and American-Indian languages to create corpora covering a large number of languages from across the world.
%U https://aclanthology.org/2023.icon-1.49
%P 534-539
Markdown (Informal)
[First Attempt at Building Parallel Corpora for Machine Translation of Northeast India’s Very Low-Resource Languages](https://aclanthology.org/2023.icon-1.49) (Atnafu Lambebo et al., ICON 2023)
ACL