本文研究了大词汇量非特定人汉语连续语音识别和理解系统中的容错技术。
In this paper, error tolerant techniques are studied for large vocabulary speaker independent Chinese continuous speech recognition and understanding systems.
然后从现代汉语疑问句的计算语言学分析入手,提出了虚拟信息顾问——问题理解子系统的模型。
Then, we put forward the model of the question understanding sub-system borrowed the idea of Chinese question analysis of computational linguistics.
本文设计和实现了面向机械设计的汉语言理解系统中事件名词本体知识库,来提高系统性能和效率。
This paper has designed and implemented the event-noun knowledge base of ontology, in order to improve the performance and efficiency of this system.
应用推荐