INSOMNet Demo and package (2003)
Author: Marshall Mayberry III
INSOMNet is a subysmbolic sentence processing system that produces explicit and graded semantic graph representations. The novel technique of semantic self-organization allows the network to learn typical semantic dependencies between nodes in a graph that helps the INSOMNet process novel sentences. The technique makes it possible to assign case roles flexibly, while retaining the cogntively plausible behavior that characterizes connectionist modeling. INSOMNet has been shown to scale up to to sentences of realistic complexity, including those with dysfluencies in the input and damage in the network. The network also exhibits the crucial cognitive properties of incremental processing, expectations, semantic priming, and nonmonotonoic revision of an interpretation during sentence processing. INSOMNet therefore constitutes a significant step towards building a cogntive parser that works with everyday language that people use.

URL
Marshall R. Mayberry III Ph.D. Alumni martym at coli dot uni-sb dot
Risto Miikkulainen Faculty risto [at] cs utexas edu
Incremental Nonmonotonic Parsing through Semantic Self-Organization 2003
Marshall R. Mayberry III, PhD Thesis, Department of Computer Sciences, the University of Texas at Austin. Technical Report AI-TR-04-310.
Incremental Nonmonotonic Parsing through SemanticSelf-Organization 2003
Marshall R. Mayberry III and Risto Miikkulainen, In Proceedings of the 25th Annual Conference of the Cognitive Science Society 2003.