@inproceedings{gaikwad-etal-2023-machine,
title = "Machine Translation Advancements for Low-Resource {I}ndian Languages in {WMT}23: {CFILT}-{IITB}`s Effort for Bridging the Gap",
author = "Gaikwad, Pranav and
Doshi, Meet and
Deoghare, Sourabh and
Bhattacharyya, Pushpak",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.89/",
doi = "10.18653/v1/2023.wmt-1.89",
pages = "950--953",
abstract = "This paper is related to the submission of the CFILT-IITB team for the task called IndicMT in WMT23. The paper describes our MT systems submitted to the WMT23 IndicMT shared task. The task focused on MT system development from/to English and four low-resource North-East Indian languages, viz., Assamese, Khasi, Manipuri, and Mizo. We trained them on a small parallel corpus resulting in poor-quality systems. Therefore, we utilize transfer learning with the help of a large pre-trained multilingual NMT system. Since this approach produced the best results, we submitted our NMT models for the shared task using this approach."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaikwad-etal-2023-machine">
<titleInfo>
<title>Machine Translation Advancements for Low-Resource Indian Languages in WMT23: CFILT-IITB‘s Effort for Bridging the Gap</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Gaikwad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meet</namePart>
<namePart type="family">Doshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sourabh</namePart>
<namePart type="family">Deoghare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</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 Eighth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper is related to the submission of the CFILT-IITB team for the task called IndicMT in WMT23. The paper describes our MT systems submitted to the WMT23 IndicMT shared task. The task focused on MT system development from/to English and four low-resource North-East Indian languages, viz., Assamese, Khasi, Manipuri, and Mizo. We trained them on a small parallel corpus resulting in poor-quality systems. Therefore, we utilize transfer learning with the help of a large pre-trained multilingual NMT system. Since this approach produced the best results, we submitted our NMT models for the shared task using this approach.</abstract>
<identifier type="citekey">gaikwad-etal-2023-machine</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.89</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.89/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>950</start>
<end>953</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Translation Advancements for Low-Resource Indian Languages in WMT23: CFILT-IITB‘s Effort for Bridging the Gap
%A Gaikwad, Pranav
%A Doshi, Meet
%A Deoghare, Sourabh
%A Bhattacharyya, Pushpak
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F gaikwad-etal-2023-machine
%X This paper is related to the submission of the CFILT-IITB team for the task called IndicMT in WMT23. The paper describes our MT systems submitted to the WMT23 IndicMT shared task. The task focused on MT system development from/to English and four low-resource North-East Indian languages, viz., Assamese, Khasi, Manipuri, and Mizo. We trained them on a small parallel corpus resulting in poor-quality systems. Therefore, we utilize transfer learning with the help of a large pre-trained multilingual NMT system. Since this approach produced the best results, we submitted our NMT models for the shared task using this approach.
%R 10.18653/v1/2023.wmt-1.89
%U https://aclanthology.org/2023.wmt-1.89/
%U https://doi.org/10.18653/v1/2023.wmt-1.89
%P 950-953
Markdown (Informal)
[Machine Translation Advancements for Low-Resource Indian Languages in WMT23: CFILT-IITB’s Effort for Bridging the Gap](https://aclanthology.org/2023.wmt-1.89/) (Gaikwad et al., WMT 2023)
ACL