HACAN:a hierarchical answer-aware and context-aware network for question generation  

作　　者：Ruijun SUN Hanqin TAO Yanmin CHEN Qi LIU 

机构地区：[1]Anhui Province Key Laboratory of Big Data Analysis and Application,University of Science and Technology of China,Hefei230027,China

出　　处：《Frontiers of Computer Science》2024年第5期45-55,共11页计算机科学前沿（英文版）

基　　金：This research was partially supported by the National Key R&D Program of China(No.2021YFF0901003).

摘　　要：Question Generation(QG)is the task of generating questions according to the given contexts.Most of the existing methods are based on Recurrent Neural Networks(RNNs)for generating questions with passage-level input for providing more details,which seriously suffer from such problems as gradient vanishing and ineffective information utilization.In fact,reasonably extracting useful information from a given context is more in line with our actual needs during questioning especially in the education scenario.To that end,in this paper,we propose a novel Hierarchical Answer-Aware and Context-Aware Network(HACAN)to construct a high-quality passage representation and judge the balance between the sentences and the whole passage.Specifically,a Hierarchical Passage Encoder(HPE)is proposed to construct an answer-aware and context-aware passage representation,with a strategy of utilizing multi-hop reasoning.Then,we draw inspiration from the actual human questioning process and design a Hierarchical Passage-aware Decoder(HPD)which determines when to utilize the passage information.We conduct extensive experiments on the SQuAD dataset,where the results verify the effectivenesss of our model in comparison with several baselines.

关 键 词：question generation natural language generation natural language processing sequence to sequence 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]