Conditional pre‐trained attention based Chinese question generation

Abstract

Question generation is a promising and important area in natural language processing. According to the information of the given text, the question generation model can automatically generate a variety of questions, which are conducive to processing various subsequent tasks. Chinese question generation is a specific sub-area of question generation. Due to the characteristics of Chinese question generation tasks, many methods are not suitable for it, and the generated results are either incorrect in word order or invalid expression. In order to address such challenging problem, we propose the conditional pre-trained attention model termed A Lite BERT Conditional Question Generation (ALBERT-CQG) for Chinese question generation. Through introducing general background knowledge of the pre-trained model and conditional information of the given answers, this model has capacity of generating more valid expression. To our knowledge, we are the first to apply the conditional pre-trained attention model to Chinese question generation tasks. The experimental results on two known benchmark datasets of Chinese question answering show that the ALBERT-CQG outperforms its recent peers. K E Y W O R D SChinese question generation, conditional pre-trained attention model, general background knowledge

Attention virtual adversarial based semi‐supervised question generation

“…The learning process of GAN is divided into two stages: optimization discriminator and optimization generator, that is, the process of maximization and minimization in Equation. 1 The first stage fixes the parameters of the generator G to optimize the discriminator D, that is, for the sample x from the real distribution, make D(x) as large as possible, and for the sample G(z) from the generator G, make D(G(z)) as small as possible:…”

“…The learning process of GAN is divided into two stages: optimization discriminator and optimization generator, that is, the process of maximization and minimization in Equation 1 …”

“…In many application areas, the demand for QG is growing rapidly. QG is the dual task of answering a question, and it has aroused great interest in recent years 1–3 . QG in the field of education can be used to generate exercises and assignments, 4 and it can help chat bots have cold‐to‐start or continue conversations with human users in the field of dialogue 5 .…”