Knowledge representation for syntactic/semantic processing
Robert Bobrow, Bonnie Webber · National Conference on Artificial Intelligence · 1980
This paper describes the RUS framework for natural language processing, in which a parser incorporating a substantial ATN grammar for English interacts with a semantic interpreter to simultaneously parse and interpret input. The structure of that interaction is discussed, including the roles played by syntactic and semantic knowledge. Several implementations of the RUS framework are currently in use, sharing the same grammar, but differing in the form of their semantic component. One of these, the PSI-KLONE system, is based on a general object-centered knowledge representation system, called KL-ONE. The operation of PSI-KLONE is described, including its use of KL-ONE to support a general inference process called incremental description refinement. The last section of the paper discusses several important criteria for knowledge representation systems to be used in syntactic and semantic processing.