摘要
语句的主题提取是口语对话系统中话语分析部分的工作。目前的口语对话系统大多将自然语言处理的重点放在语法和语义平面,而忽视了对上下文语境的分析,该文提出一种基于规则的语句主题提取方法,通过自底向上与自顶向下两种分析器完成主题与用户意图的提取,为系统的自然语言生成提供更准确的领域知识,从而大大提高了系统的整体性能。
Extraction of the topic from utterances is part of the discourse analysis in a spoken dialog system.At pre-sent ,many spoken dialog systems take the key point on semantic surface,ignoring the context dependent interpretation of utterances.This paper presents an approach to extraction of user's intentions and topics through bottom-up and top-down analysis.It can provide more knowledge for system and therefore enhance the system performance greatly.
出处
《计算机工程与应用》
CSCD
北大核心
2004年第18期58-60,98,共4页
Computer Engineering and Applications
关键词
主题提取
口语对话系统
自然语言理解
topic extraction,spoken dialog system,natural language understanding