SARDSRN: A Neural Network Shift-Reduce Parser (1999)
Simple Recurrent Networks (SRNs) have been widely used in natural language tasks. SARDSRN extends the SRN by explicitly representing the input sequence in a SARDNET self-organizing map. The distributed SRN component leads to good generalization and robust cognitive properties, whereas the SARDNET map provides exact representations of the sentence constituents. This combination allows SARDSRN to learn to parse sentences with more complicated structure than can the SRN alone, and suggests that the approach could scale up to realistic natural language.
In Proceedings of the 16th Annual International Joint Conference on Artificial Intelligence (IJCAI-99), 820-825, Stockholm, Sweden, 1999. San Francisco, CA: Kaufmann.

Marshall R. Mayberry III Ph.D. Alumni marty mayberry [at] gmail com
Risto Miikkulainen Faculty risto [at] cs utexas edu