A Study on an Effect of Using Deep Learning in Thai-English Machine Translation Processes

Deep learning has been used in many fields including natural language processing. This paper aims to study the effect of applying deep learning in machine translation processes including word segmentation and translation model generation. We compare the results of the process from traditional statistical method and deep learning and analyze the difference. From experiment, the results indicated that the processes from deep learning obtained higher score in overall. Word segmentation from Bidirectional neural network yielded 0.861 f1 score which was higher than standard n-gram based system for 0.081. The translation results within dataset show that the neural-network-based translation got the best BLEU score in average for 0.43 in which are higher than the traditional statistical approach for 0.16. The result analysis indicates that the neural-network-based translation can translate better for Thai sentences containing unknown words and those with numerical classifier expression.