Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

The main goal of the SNAP project is to build a massively parallel computer capable of fast and accurate natural language processing [3]. Under NSF funding, a parallel computer was built in the Parallel Knowledge Processing Laboratory at USC and software was developed to operate the machine [2]. The approach in designing SNAP was to find a knowledge representation and a reasoning paradigm useful for natural language processing which exibits massive parallelism. We have selected marker-passing on semantic networks as a way to represent and process linguistic knowledge.

REFERENCES

• 1: Chung, M. and Moldovan, D., "Memory-Based Parsing with Integrated Syntactic and Semantic Analysis on SNAP", Technical Report PKPL 91--10, Dept. of Electrical Engineering-Systems, University of Southern California, 1991.
• 2: DeMara, R. and Moldovan, D., "The SNAP-1 Parallel AI Prototype", Technical Report PKPL 92-3, Dept. of Electrical Engineering-Systems, University of Southern California, 1992.
• 3: Dan Moldovan , Wing Lee , Changhwa Lin , Minhwa Chung, SNAP: Parallel Processing Applied to AI, Computer, v.25 n.5, p.39-49, May 1992 [doi>10.1109/2.144394]
• 4: Riesbeck, C. and Martin, C., "Direct Memory Access Parsing," Report 354, Dept. of Computer Science, Yale University, 1985.