@inproceedings{p-m-etal-2024-mtnlp,
title = "{MTNLP}-{IIITH}: Machine Translation for Low-Resource {I}ndic Languages",
author = "P M, Abhinav and
Shetye, Ketaki and
Krishnamurthy, Parameswari",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Ninth Conference on Machine Translation",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wmt-1.65",
doi = "10.18653/v1/2024.wmt-1.65",
pages = "751--755",
abstract = "Machine Translation for low-resource languages presents significant challenges, primarily due to limited data availability. We have a baseline model and a primary model. For the baseline model, we first fine-tune the mBART model (mbart-large-50-many-to-many-mmt) for the language pairs English-Khasi, Khasi-English, English-Manipuri, and Manipuri-English. We then augment the dataset by back-translating from Indic languages to English. To enhance data quality, we fine-tune the LaBSE model specifically for Khasi and Manipuri, generating sentence embeddings and applying a cosine similarity threshold of 0.84 to filter out low-quality back-translations. The filtered data is combined with the original training data and used to further fine-tune the mBART model, creating our primary model. The results show that the primary model slightly outperforms the baseline model, with the best performance achieved by the English-to-Khasi (en-kh) primary model, which recorded a BLEU score of 0.0492, a chrF score of 0.3316, and a METEOR score of 0.2589 (on a scale of 0 to 1), with similar results for other language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="p-m-etal-2024-mtnlp">
<titleInfo>
<title>MTNLP-IIITH: Machine Translation for Low-Resource Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">P M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ketaki</namePart>
<namePart type="family">Shetye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Conference on Machine Translation</title>
</titleInfo>
<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">Philipp</namePart>
<namePart type="family">Koehn</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">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine Translation for low-resource languages presents significant challenges, primarily due to limited data availability. We have a baseline model and a primary model. For the baseline model, we first fine-tune the mBART model (mbart-large-50-many-to-many-mmt) for the language pairs English-Khasi, Khasi-English, English-Manipuri, and Manipuri-English. We then augment the dataset by back-translating from Indic languages to English. To enhance data quality, we fine-tune the LaBSE model specifically for Khasi and Manipuri, generating sentence embeddings and applying a cosine similarity threshold of 0.84 to filter out low-quality back-translations. The filtered data is combined with the original training data and used to further fine-tune the mBART model, creating our primary model. The results show that the primary model slightly outperforms the baseline model, with the best performance achieved by the English-to-Khasi (en-kh) primary model, which recorded a BLEU score of 0.0492, a chrF score of 0.3316, and a METEOR score of 0.2589 (on a scale of 0 to 1), with similar results for other language pairs.</abstract>
<identifier type="citekey">p-m-etal-2024-mtnlp</identifier>
<identifier type="doi">10.18653/v1/2024.wmt-1.65</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.65</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>751</start>
<end>755</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MTNLP-IIITH: Machine Translation for Low-Resource Indic Languages
%A P M, Abhinav
%A Shetye, Ketaki
%A Krishnamurthy, Parameswari
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Ninth Conference on Machine Translation
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F p-m-etal-2024-mtnlp
%X Machine Translation for low-resource languages presents significant challenges, primarily due to limited data availability. We have a baseline model and a primary model. For the baseline model, we first fine-tune the mBART model (mbart-large-50-many-to-many-mmt) for the language pairs English-Khasi, Khasi-English, English-Manipuri, and Manipuri-English. We then augment the dataset by back-translating from Indic languages to English. To enhance data quality, we fine-tune the LaBSE model specifically for Khasi and Manipuri, generating sentence embeddings and applying a cosine similarity threshold of 0.84 to filter out low-quality back-translations. The filtered data is combined with the original training data and used to further fine-tune the mBART model, creating our primary model. The results show that the primary model slightly outperforms the baseline model, with the best performance achieved by the English-to-Khasi (en-kh) primary model, which recorded a BLEU score of 0.0492, a chrF score of 0.3316, and a METEOR score of 0.2589 (on a scale of 0 to 1), with similar results for other language pairs.
%R 10.18653/v1/2024.wmt-1.65
%U https://aclanthology.org/2024.wmt-1.65
%U https://doi.org/10.18653/v1/2024.wmt-1.65
%P 751-755
Markdown (Informal)
[MTNLP-IIITH: Machine Translation for Low-Resource Indic Languages](https://aclanthology.org/2024.wmt-1.65) (P M et al., WMT 2024)
ACL