作者: Boris Katz
DOI:
关键词:
摘要: This paper describes the START Information Server built at MIT Artificial Intelligence Laboratory. Available on World Wide Web since December 1993, provides users with access to multi-media information in response questions formulated English. Over last 3 years, answered hundreds of thousands from all over world. The is two foundations: sentence-level Natural Language processing capability provided by system and idea natural language annotations for segments. starts an overview then explains how annotating segments collections English sentences makes it possible use power service access. The ends a proposal annotate Web.