Harmonic Grammars for Formal Languages

Abstract

Basic connectionist principles imply that grammars should take the form of systems of parallel soft constraints defining an optimization problem the solutions to which are the well-formed structures in the language. Such Harmonic Grammars have been successfully applied to a number of problems in the theory of natural languages. Here it is shown that formal languages too can be specified by Harmonic Grammars, rather than by conventional serial re-write rule systems.

Cite

Text

Smolensky. "Harmonic Grammars for Formal Languages." Neural Information Processing Systems, 1992.

Markdown

[Smolensky. "Harmonic Grammars for Formal Languages." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/smolensky1992neurips-harmonic/)

BibTeX

@inproceedings{smolensky1992neurips-harmonic,
  title     = {{Harmonic Grammars for Formal Languages}},
  author    = {Smolensky, Paul},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {847-854},
  url       = {https://mlanthology.org/neurips/1992/smolensky1992neurips-harmonic/}
}