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...
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...
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...