A simple but practical method: How to improve the usage of entities in the Chinese question generation

Abstract

Answer-aware question generation aims to generate answerable questions from a given paragraph and answer. Most of the current models concatenated entity information into word embeddings to improve the model's learning ability for special entities, but this method is inefficient for utilizing these information and has accumulated errors. In addition, the majority of research focuses on English, with less exploration in languages such as Chinese. Combining the differences between languages, we propose three methods for incorporating entity information in paragraphs and answers into the training corpus. The corpus processed by these methods can enable the model to have the ability to learn entities autonomously. The experimental results show that our methods can improve most mainstream models and enhance the learning ability of the model for special entities.