Topic labeling of broadcast news stories in the informedia digital video library
暂无分享,去创建一个
This paper describes the implementation of a topic labeling component for the Informedia Digital Video Library. Each news story recorded from the evening news is assigned to one of 3178 topic categories using a K-nearest neighbor classification algorithm. In preliminary tests, the system achieved recall of 0.49 1 with relevance of 0.482 when up to 5 topics could be assigned to a news story.
[1] Diane Vizine-Goetz,et al. Evaluating Dewey concepts as a knowledge base for automatic subject assignment , 1997, DL '97.
[2] Richard M. Schwartz,et al. A maximum likelihood model for topic classification of broadcast news , 1997, EUROSPEECH.
[3] Gerard Salton,et al. The SMART Retrieval System , 1971 .
[4] Takeo Kanade,et al. Informedia Digital Video Library , 1995, CACM.