@inproceedings{laskar-etal-2022-investigation,
title = "Investigation of Multilingual Neural Machine Translation for {I}ndian Languages",
author = "Laskar, Sahinur Rahman and
Manna, Riyanka and
Pakray, Partha and
Bandyopadhyay, Sivaji",
booktitle = "Proceedings of the 9th Workshop on Asian Translation",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2022.wat-1.9",
pages = "78--81",
abstract = "In the domain of natural language processing, machine translation is a well-defined task where one natural language is automatically translated to another natural language. The deep learning-based approach of machine translation, known as neural machine translation attains remarkable translational performance. However, it requires a sufficient amount of training data which is a critical issue for low-resource pair translation. To handle the data scarcity problem, the multilingual concept has been investigated in neural machine translation in different settings like many-to-one and one-to-many translation. WAT2022 (Workshop on Asian Translation 2022) organizes (hosted by the COLING 2022) Indic tasks: English-to-Indic and Indic-to-English translation tasks where we have participated as a team named CNLP-NITS-PP. Herein, we have investigated a transliteration-based approach, where Indic languages are transliterated into English script and shared sub-word level vocabulary during the training phase. We have attained BLEU scores of 2.0 (English-to-Bengali), 1.10 (English-to-Assamese), 4.50 (Bengali-to-English), and 3.50 (Assamese-to-English) translation, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laskar-etal-2022-investigation">
<titleInfo>
<title>Investigation of Multilingual Neural Machine Translation for Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sahinur</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riyanka</namePart>
<namePart type="family">Manna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Partha</namePart>
<namePart type="family">Pakray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Asian Translation</title>
</titleInfo>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the domain of natural language processing, machine translation is a well-defined task where one natural language is automatically translated to another natural language. The deep learning-based approach of machine translation, known as neural machine translation attains remarkable translational performance. However, it requires a sufficient amount of training data which is a critical issue for low-resource pair translation. To handle the data scarcity problem, the multilingual concept has been investigated in neural machine translation in different settings like many-to-one and one-to-many translation. WAT2022 (Workshop on Asian Translation 2022) organizes (hosted by the COLING 2022) Indic tasks: English-to-Indic and Indic-to-English translation tasks where we have participated as a team named CNLP-NITS-PP. Herein, we have investigated a transliteration-based approach, where Indic languages are transliterated into English script and shared sub-word level vocabulary during the training phase. We have attained BLEU scores of 2.0 (English-to-Bengali), 1.10 (English-to-Assamese), 4.50 (Bengali-to-English), and 3.50 (Assamese-to-English) translation, respectively.</abstract>
<identifier type="citekey">laskar-etal-2022-investigation</identifier>
<location>
<url>https://aclanthology.org/2022.wat-1.9</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>78</start>
<end>81</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigation of Multilingual Neural Machine Translation for Indian Languages
%A Laskar, Sahinur Rahman
%A Manna, Riyanka
%A Pakray, Partha
%A Bandyopadhyay, Sivaji
%S Proceedings of the 9th Workshop on Asian Translation
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Gyeongju, Republic of Korea
%F laskar-etal-2022-investigation
%X In the domain of natural language processing, machine translation is a well-defined task where one natural language is automatically translated to another natural language. The deep learning-based approach of machine translation, known as neural machine translation attains remarkable translational performance. However, it requires a sufficient amount of training data which is a critical issue for low-resource pair translation. To handle the data scarcity problem, the multilingual concept has been investigated in neural machine translation in different settings like many-to-one and one-to-many translation. WAT2022 (Workshop on Asian Translation 2022) organizes (hosted by the COLING 2022) Indic tasks: English-to-Indic and Indic-to-English translation tasks where we have participated as a team named CNLP-NITS-PP. Herein, we have investigated a transliteration-based approach, where Indic languages are transliterated into English script and shared sub-word level vocabulary during the training phase. We have attained BLEU scores of 2.0 (English-to-Bengali), 1.10 (English-to-Assamese), 4.50 (Bengali-to-English), and 3.50 (Assamese-to-English) translation, respectively.
%U https://aclanthology.org/2022.wat-1.9
%P 78-81
Markdown (Informal)
[Investigation of Multilingual Neural Machine Translation for Indian Languages](https://aclanthology.org/2022.wat-1.9) (Laskar et al., WAT 2022)
ACL