title: SARDSRN: A NEURAL NETWORK SHIFT-REDUCE PARSER creator: Mayberry, Marshall R. creator: Miikkulainen, Risto subject: Language subject: Neural Nets subject: Artificial Intelligence description: 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. date: 1999 type: Conference Paper type: PeerReviewed format: application/pdf identifier: http://cogprints.org/2646/1/mayberry.sardsrn.pdf identifier: Mayberry, Marshall R. and Miikkulainen, Risto (1999) SARDSRN: A NEURAL NETWORK SHIFT-REDUCE PARSER. [Conference Paper] relation: http://cogprints.org/2646/