SARDSRN: A Neural Network Shift-Reduce Parser

Mayberry, Marshall R.; Miikkulainen, Risto

SARDSRN: A Neural Network Shift-Reduce Parser

Marshall R. Mayberry, Risto Miikkulainen

Download BibTeX Cite

Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence. Machine Learning. Pages 820-826.

Abstract

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.

Marshall R. Mayberry, and Risto Miikkulainen. 1999. SARDSRN: A Neural Network Shift-Reduce Parser. In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, IJCAI-99. IJCAI, 820–826. https://ijcai.org/proceedings/1999/117

@inproceedings{ijcai1999p117,
  title     = {SARDSRN: A Neural Network Shift-Reduce Parser},
  author    = {Mayberry, Marshall R. and Miikkulainen, Risto},
  booktitle = {Proceedings of the Sixteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-99}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Thomas Dean},
  pages     = {820--826},
  year      = {1999},
  note      = {Machine Learning},
  url       = {https://ijcai.org/proceedings/1999/117},
}

TY  - CPAPER
TI  - SARDSRN: A Neural Network Shift-Reduce Parser
AU  - Mayberry, Marshall R.
AU  - Miikkulainen, Risto
T2  - Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, IJCAI-99
PB  - International Joint Conferences on Artificial Intelligence
PY  - 1999
SP  - 820
EP  - 826
UR  - https://ijcai.org/proceedings/1999/117
ER  -