<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Machine translation (MT) is an important use case in natural language processing (NLP) that converts a source language to a target language automatically. Modern intelligent system or artificial intelligence (AI) uses a machine learning approach and the machine has acquired learning ability using datasets. Nowadays, in the MT domain, the neural machine translation (NMT) system has almost replaced the statistical machine translation (SMT) system. The NMT systems use a deep learning framework in their implementation. To achieve higher accuracy during the training of the NMT model, extensive hyper-parameter tuning is required. The paper highlights the significance of hyper-parameter tuning in various machine learning algorithms. And as a case study, in-house experimentation was conducted on a low-resource English–Bangla language pair by designing an NMT system and the significance of various hyper-parameter optimizations was analyzed while evaluating its performance with an automatic metric BLEU. The BLEU scores obtained for the first, second, and third randomly picked test sentences are 4.1, 3.2, and 3.01, respectively.</p>
</abstract>

Machine translation (MT) is an important use case in natural language processing (NLP) that converts a source language to a target language automatically. Modern intelligent system or artificial intelligence (AI) uses a machine learning approach and the machine has acquired learning ability using datasets. Nowadays, in the MT domain, the neural machine translation (NMT) system has almost replaced the statistical machine translation (SMT) system. The NMT systems use a deep learning framework in their implementation. To achieve higher accuracy during the training of the NMT model, extensive hyper-parameter tuning is required. The paper highlights the significance of hyper-parameter tuning in various machine learning algorithms. And as a case study, in-house experimentation was conducted on a low-resource English–Bangla language pair by designing an NMT system and the significance of various hyper-parameter optimizations was analyzed while evaluating its performance with an automatic metric BLEU. The BLEU scores obtained for the first, second, and third randomly picked test sentences are 4.1, 3.2, and 3.01, respectively.

Hyper-parameter optimization in neural-based translation systems: A case study

Deparment of Mathematical and Computer Science

University of Petroleum and Energy Studies

International Journal on Smart Sensing and Intelligent Systems

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Hyper-parameter optimization in neural-based translation systems: A case study"}

Machine translation (MT) is an important use case in natural language processing (NLP) that converts a source language to a target language automatically....

Hyper-parameter optimization in neural-based translation systems: A case study

Article Category: Article

Publicado en línea: 25 sept 2023

Páginas: -

Recibido: 22 feb 2023

DOI: https://doi.org/10.2478/ijssis-2023-0010

Palabras clave
Neural machine translation, LSTM, transformer, GAN, hyper-parameter

© 2023 Goutam Datta et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Hyper-parameter optimization in neural-based translation systems: A case study

Article Category: Article

Publicado en línea: 25 sept 2023

Páginas: -

Recibido: 22 feb 2023

DOI: https://doi.org/10.2478/ijssis-2023-0010

Palabras claveNeural machine translation, LSTM, transformer, GAN, hyper-parameter

© 2023 Goutam Datta et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Palabras clave
Neural machine translation, LSTM, transformer, GAN, hyper-parameter