Subsymbolic Parsing of Sequences: The SARDSRN model
Active from 1998 - 1999
The SARDSRN model demonstrates how the performance of a Simple Recurrent Network (SRN) parser can be enhanced significantly by the addition of a SARDNET module. SARDNET is an extension to the Self-Organizing Map architecture (SOM) which allows self-organization of sequences. The SARDNET module in the SARDSRN parser explicitly represents the input sequence in a 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.
Marshall R. Mayberry III Ph.D. Alumni martym at coli dot uni-sb dot
Hong Ming Yeh Formerly affiliated Ph.D. Student hongming [at] cs utexas edu
SARDSRN: A Neural Network Shift-Reduce Parser 1999
Marshall R. Mayberry III and Risto Miikkulainen, In Proceedings of the 16th Annual International Joint Conference on Artificial Intelligence (IJCAI-99), pp. 820-825, Stockholm, Sweden 1999. San Francisco, CA: Kaufmann.
MIR Sentence Processing Package The MIR Sentence Processing package contains the C source code for the MIR system, as well as a selection of scripts wi... 1998