反绎学习支持下的自动问答及其应用

Automatic Question and Answering Supported by Abductive Learning and Its Application

自动问答技术可以为用户提供快速且准确的信息检索和问题解答服务。然而,目前常见方法生成的答案存在不准确和不完整的问题,以及实体识别和关系抽取效果不准确,且答案不够自然。为此,提出基于反绎学习的自动问答方法,使用基于知识图谱的问答推理优化基于生成的问答,进一步从整体的反绎学习框架角度来优化实体识别和关系抽取方法,并将所提方法应用于《数据结构》课程的学习。结果表明,基于反绎学习的自动问答方法,可以改进基于生成的问答和基于知识图谱的问答两者的不足,提高问答系统的准确性。

Automatic question and answering(QA)techniques can provide users with fast and accurate information retrieval and problem-solving services.However,the answers generated by current common methods are often inaccurate,incom-plete and unnatural.To this end,an abductive learning-based automatic QA method is proposed,which employs knowl-edge graph-based QA to infer and optimize the generation-based QA.Furthermore,the overall abductive learning frame-work is employed to optimize entity recognition and relationship extraction methods.The proposed method is applied to self-learning of the“Data Structures”course.The results show that the abductive learning-based automatic QA method can overcome the shortcomings of both the generation-based QA and knowledge graph-based QA,and improve the accu-racy of the QA system.