Enhanced Back-Translation for Low Resource Neural Machine Translation Using Self-training

Abstract

Many language pairs are low resourcethe amount and/or quality of parallel data is not sufficient to train a neural machine translation (NMT) model which can reach an acceptable standard of accuracy. Many works have explored the use of the easier-to-get monolingual data to improve the performance of translation models in this category of languagesand even high resource languages. The most successful of such works is the back-translationusing the translations of the target language monolingual data to increase the amount of the training data. The quality of the backward modeltrained on the available parallel datahas been shown to determine the performance of the back-translation approach. Many approaches have been explored to improve the performance of this model especially in low resource languages where the amount of parallel data is not sufficient to train an acceptable backward model. Among such works are the use of self-learning and the iterative back-translation. These methods were shown to perform better than the standard back-translation. This work presents the iterative self-training approach as an improvement over the self-learning approach to further enhance the performance of the backward model. Over several iterations, the synthetic data generated by the backward model is used to improve its performance through forward translation. Experiments have shown that the method outperforms both the standard back-translation and self-learning approach on IWSLT'14 English-German low resource NMT. While the method also outperforms the iterative back-translation, though slightly, the number of models required to be trained is reduced exactly by the number of iterations.

Improving BERTScore for Machine Translation Evaluation Through Contrastive Learning

“…Hausa is a low-resource language, there are limited sources of domain-specific parallel data between it and English [44], [45], [46], [47]. For the news domain we use the Khamenei parallel corpus derived from news articles and speeches on khamenei.ir, which can now only be accessed by Wayback Machine.…”

Задача Создания Синтетических Корпусов Для Малоресурсного Языка

“…The calculation of the probability of a class of synonyms by the formula (3) will be as follows: x shows the biggest (maximum) [11][12][13][14][15].…”

A Mongolian–Chinese Neural Machine Translation Method Based on Semantic-Context Data Augmentation

“…Zhang et al [14] proposed using self-learning algorithms to generate pseudo-parallel corpora from monolingual data, and also using two NMT models in a multitasking learning framework to predict translations and reorder source sentences. Abdulsumin et al [15] proposed an improvement on self-learning methods, namely iterative self training methods. Hoang et al [16] improved the performance of NMT by iterating reverse translation in high-and low-resource situations.…”