基于自然语言理解的在线答疑系统设计与实现  

Design and implementation of online answer system based on natural language understanding

作　　者：赵静[1,2] 党丽琼 

机构地区：[1]西安理工大学,陕西西安710105 [2]陕西航天职工大学

出　　处：《计算机时代》2015年第5期10-12,共3页Computer Era

摘　　要：基于自然语言理解的相似度计算仍是计算机语言处理技术尚需深入研究的内容。通过在"知网"知识表示的基础上,综合考虑深度和密度两方面的影响因素,利用一种较为成熟的改进的多因素语义相似度处理算法,基于全文检索匹配技术,设计并实现了一个限定领域内的在线答疑系统。实例运行结果表明,系统可靠性较高,且答疑效果较为明显,达到了预期目标。The similarity calculation based on natural language understanding is still a research content of the computer language processing technology. Based on the knowledge representation of ＂HowNet＂, considering the both factors of depth and density, by using a more sophisticated multivariate semantic similarity algorithm, and with a full-text search matching technology, an online answer system in the limited field is designed and implemented. The experimental results show that, the system is reliable, the answer effect is more obvious, and the desired goal is achieved.

关 键 词：自然语言理解 语义相似度 全文检索 在线答疑系统 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]