Automatic Question and Answer Generation from Thai Sentences

Automatic questions and answers generated are challenging tasks that attract broad engagement. This paper presents an automatic question and answer generation from Thai sentences. We adopted question classification to predict the expected wh-question type before generating question and answer. This experimental study tested the question and answer generation on the sampling set of 300 Thai sentences based on the wh-question type that trained classify category from 15,000 samples. Automatic evaluation is performed on a reference set using the BLEU metrics and human evaluation. The experiment results show that the proposed method can generate questions and answers from Thai sentences. However, the performance based on the efficiency of Natural Language Processing includes tokenization, Named Entities Recognition, and Part of Speech tagging task because it could effectively extract focusing words correctly and suitable to answer the question that enhances the trustworthiness of future work in question and answer generation from Thai texts.