Neural Machine Translation on Scarce-Resource Condition: A case-study on Persian-English

TL;DR

This paper evaluates neural machine translation for Persian-English under scarce-resource conditions, optimizing model parameters, preprocessing, and loss functions to improve translation quality.

Contribution

It introduces tailored adjustments and a new loss function for NMT in scarce-resource Persian-English translation, enhancing BLEU scores.

Findings

Preprocessing increased BLEU score by about 1 point.

Modified loss function improved BLEU score by 1.87 points.

Optimized parameters for translation and transliteration tasks.

Abstract

Neural Machine Translation (NMT) is a new approach for Machine Translation (MT), and due to its success, it has absorbed the attention of many researchers in the field. In this paper, we study NMT model on Persian-English language pairs, to analyze the model and investigate the appropriateness of the model for scarce-resourced scenarios, the situation that exists for Persian-centered translation systems. We adjust the model for the Persian language and find the best parameters and hyper parameters for two tasks: translation and transliteration. We also apply some preprocessing task on the Persian dataset which yields to increase for about one point in terms of BLEU score. Also, we have modified the loss function to enhance the word alignment of the model. This new loss function yields a total of 1.87 point improvements in terms of BLEU score in the translation quality.