摘要
在HNC理论框架的指导下,充分考虑了短文本的领域、情境和背景,提取了对短文本语义影响较大的特征填充语境框架.实验表明该框架能够较好地理解短文本的上下文信息,并且有效处理了短文本语义块的分离、句蜕和歧义等现象,框架提取准确率较高,而且系统资源开销较少,运行效率较高.
Base on HNC theory, this paper considers the domain, situation, background of a short text sufficiently and extracts the characters which have more effects on semantic comprehend. Then it fills the frame. Experiments show that the algorithm has better comprehend on short text context and deals with the separation, degradation and different meanings of semantic block effectively. The frame is more accurate and the algorithm costs little resource of the system and has good performance.
出处
《北京工商大学学报（自然科学版）》
CAS
2007年第5期49-52,63,共5页
Journal of Beijing Technology and Business University:Natural Science Edition
基金
北京市教育委员会科技发展计划重点项目(KM200510009005)
关键词
HNC理论
语境框架
短文本
算法
HNC theory
context framework model
short text
algorithm
