In this subsection, we provide a brief summary of how START works. For greater detail, see the appended paper, Multi-media Information Access using Natural Language Annotations.
The START server is built on two foundations: the sentence-level Natural Language processing capability provided by the START Natural Language system (Katz [1990]) and the idea of natural language annotations for multi-media information segments. We start with an overview of sentence-level processing in the START system and then explain how annotating information segments with collections of English sentences makes it possible to use the power of sentence-level natural language processing in the service of multi-media information access.