摘要
伴随自然语言处理快速发展,自动问答系统(Question&Answer,QA)受到研究者的广泛关注。基于表格的自动问答(Table QA)实质是在给定自然语言形式的问题文本条件下,利用表格知识库信息进行查询推理得到答案的过程。从语义解析方法角度分析了基于表格知识库的问答模型、算法特点及其相关问题,同时结合人工智能技术的发展,重点探讨了表格自动问答技术的难点以及未来可能的挑战。
With the rapid development of Natural Language Processing(NLP),automatic Question&Answer(QA)system has attracted the attention of researchers.The essence of Table QA is the process of using the information of the table knowledge base to query and reason,and get the answer under the condition of the given question text in the form of natural language.From the perspective of semantic analysis method,this paper analyzes the question answering model,algorithm,data set and other related problems based on tabular knowledge base.At the same time,combined with the development of artificial intelligence technology,the paper focuses on the difficulties and possible future challenges of table automatic question answering technology.
作者
李智
王震
杨赋庚
奚雪峰
LI Zhi;WANG Zhen;YANG Fugeng;Xi Xuefeng(Suzhou University of Science and Technology,Suzhou,Jiangsu 215009,China;Suzhou Public Security Bureau,Suzhou,Jiangsu 215000,China)
出处
《计算机工程与应用》
CSCD
北大核心
2021年第13期67-76,共10页
Computer Engineering and Applications
基金
国家自然科学基金(61876217,61672371)
江苏省“六大人才高峰”高层次人才项目(XYDXX-086)
苏州市科技发展计划产业前瞻性项目(SYG201817)。
关键词
自然语言处理
自动问答
人工智能
深度学习
Natural Language Processing(NLP)
automatic question answering
artificial intelligence
deep learning