ANLP
2000
14 years 9 months ago
2000
We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
151
click to vote
AMCP
1998
Springer
15 years 12 days ago
1998
Springer
Automatic indexing to video data is in strong demand to cope with the increasing amount. We propose an automatic indexing method for television news video, which indexes to shots c...
ICIP
2005
IEEE
15 years 9 months ago
2005
IEEE
This paper presents a method to infer hidden semantic cues by accumulating the knowledge learned from relevance feedback sessions. We propose to explicitly represent a semantic sp...