@inproceedings{pramodya-2023-exploring,
title = "Exploring Low-resource Neural Machine Translation for {S}inhala-{T}amil Language Pair",
author = "Pramodya, Ashmari",
editor = "Hardalov, Momchil and
Kancheva, Zara and
Velichkov, Boris and
Nikolova-Koleva, Ivelina and
Slavcheva, Milena",
booktitle = "Proceedings of the 8th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-stud.10",
pages = "87--97",
abstract = "At present, Neural Machine Translation is a promising approach for machine translation. Transformer-based deep learning architectures in particular show a substantial performance increase in translating between various language pairs. However, many low-resource language pairs still struggle to lend themselves to Neural Machine Translation due to their data-hungry nature. In this article, we investigate methods of expanding the parallel corpus to enhance translation quality within a model training pipeline, starting from the initial collection of parallel data to the training process of baseline models. Grounded on state-of-the-art Neural Machine Translation approaches such as hyper-parameter tuning, and data augmentation with forward and backward translation, we define a set of best practices for improving Tamil-to-Sinhala machine translation and empirically validate our methods using standard evaluation metrics. Our results demonstrate that the Neural Machine Translation models trained on larger amounts of back-translated data outperform other synthetic data generation approaches in Transformer base training settings. We further demonstrate that, even for language pairs with limited resources, Transformer models are able to tune to outperform existing state-of-the-art Statistical Machine Translation models by as much as 3.28 BLEU points in the Tamil to Sinhala translation scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pramodya-2023-exploring">
<titleInfo>
<title>Exploring Low-resource Neural Machine Translation for Sinhala-Tamil Language Pair</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashmari</namePart>
<namePart type="family">Pramodya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Momchil</namePart>
<namePart type="family">Hardalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zara</namePart>
<namePart type="family">Kancheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boris</namePart>
<namePart type="family">Velichkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Nikolova-Koleva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milena</namePart>
<namePart type="family">Slavcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>At present, Neural Machine Translation is a promising approach for machine translation. Transformer-based deep learning architectures in particular show a substantial performance increase in translating between various language pairs. However, many low-resource language pairs still struggle to lend themselves to Neural Machine Translation due to their data-hungry nature. In this article, we investigate methods of expanding the parallel corpus to enhance translation quality within a model training pipeline, starting from the initial collection of parallel data to the training process of baseline models. Grounded on state-of-the-art Neural Machine Translation approaches such as hyper-parameter tuning, and data augmentation with forward and backward translation, we define a set of best practices for improving Tamil-to-Sinhala machine translation and empirically validate our methods using standard evaluation metrics. Our results demonstrate that the Neural Machine Translation models trained on larger amounts of back-translated data outperform other synthetic data generation approaches in Transformer base training settings. We further demonstrate that, even for language pairs with limited resources, Transformer models are able to tune to outperform existing state-of-the-art Statistical Machine Translation models by as much as 3.28 BLEU points in the Tamil to Sinhala translation scenarios.</abstract>
<identifier type="citekey">pramodya-2023-exploring</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-stud.10</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>87</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Low-resource Neural Machine Translation for Sinhala-Tamil Language Pair
%A Pramodya, Ashmari
%Y Hardalov, Momchil
%Y Kancheva, Zara
%Y Velichkov, Boris
%Y Nikolova-Koleva, Ivelina
%Y Slavcheva, Milena
%S Proceedings of the 8th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F pramodya-2023-exploring
%X At present, Neural Machine Translation is a promising approach for machine translation. Transformer-based deep learning architectures in particular show a substantial performance increase in translating between various language pairs. However, many low-resource language pairs still struggle to lend themselves to Neural Machine Translation due to their data-hungry nature. In this article, we investigate methods of expanding the parallel corpus to enhance translation quality within a model training pipeline, starting from the initial collection of parallel data to the training process of baseline models. Grounded on state-of-the-art Neural Machine Translation approaches such as hyper-parameter tuning, and data augmentation with forward and backward translation, we define a set of best practices for improving Tamil-to-Sinhala machine translation and empirically validate our methods using standard evaluation metrics. Our results demonstrate that the Neural Machine Translation models trained on larger amounts of back-translated data outperform other synthetic data generation approaches in Transformer base training settings. We further demonstrate that, even for language pairs with limited resources, Transformer models are able to tune to outperform existing state-of-the-art Statistical Machine Translation models by as much as 3.28 BLEU points in the Tamil to Sinhala translation scenarios.
%U https://aclanthology.org/2023.ranlp-stud.10
%P 87-97
Markdown (Informal)
[Exploring Low-resource Neural Machine Translation for Sinhala-Tamil Language Pair](https://aclanthology.org/2023.ranlp-stud.10) (Pramodya, RANLP 2023)
ACL