融合知识图谱和语义匹配的医疗问答系统OACSTPCD
Medical question answering system integrating knowledge graph and semantic matching
问答系统是自然语言处理领域中的一项重要任务,常应用于医疗服务.传统的问答系统通过知识图谱的实体关系匹配返回相应的尾实体作为答案,然而,倘若实体或关系无法识别,又或者在知识图谱中并不存在相应的实体关系,问答将无法继续进行.为了解决这一问题,建立一种融合知识图谱和语义匹配模型的中文医疗问答混合系统.当所提问题无法在知识图谱中进行实体关系匹配时,该模型能继续从问答对数据集中找到最相似的问题,并返回相应结果作为答案.在语义匹配模型方面,结合中文医疗相似问…查看全部>>
Question answering system is an important task in the field of natural language processing,which is often used in medical service.The traditional question answering system can return the corresponding tail entity as the answer by means of the entity and relationship matching of the knowledge graph.However,if the entity or relationship is not recognized or there is no corresponding entity relationship in the knowledge graph,the question answering can not be c…查看全部>>
徐若卿
三峡大学 计算机与信息学院,湖北 宜昌 443000
电子信息工程
医疗问答系统知识图谱语义匹配问答对数据集相似问题对双曲距离度量
question answering systemknowledge graphsemantic matchingquestion answering on datasetsimilar problem pairshyperbolic distance metric
《现代电子技术》 2024 (8)
49-54,6
评论