Question Generation in the Thai Language Using MT5

Abstract

There are numerous publications of Question Generation (QG) in English but few in Thai. More than a million question-answer pairs are available in the English language, compared with only around 12,000 question-answer pairs in the Thai language. This paper presents a method to improve automatic Thai answer-agnostic QG from a dataset of insufficient size. Our evaluation showed that a QG model which was trained by the pre-trained model MT5 from a Thai dataset achieved a BLEU-1 score of 56.19. We proposed a method to generate synthetic data and an additional mechanism by using a single pre-trained model. Our best model outperformed the previous model by achieving a BLEU-1 score of 59.03. The results from the human evaluation in fluency score was 4.40, the relevance score 4.65, and the answer-ability score 4.7 out of 5.0.