A Connectionist Symbol Manipulator That Discovers the Structure of Context-Free Languages
Abstract
We present a neural net architecture that can discover hierarchical and re(cid:173) cursive structure in symbol strings. To detect structure at multiple levels, the architecture has the capability of reducing symbols substrings to single symbols, and makes use of an external stack memory. In terms of formal languages, the architecture can learn to parse strings in an LR(O) context(cid:173) free grammar. Given training sets of positive and negative exemplars, the architecture has been trained to recognize many different grammars. The architecture has only one layer of modifiable weights, allowing for a straightforward interpretation of its behavior.
Cite
Text
Mozer and Das. "A Connectionist Symbol Manipulator That Discovers the Structure of Context-Free Languages." Neural Information Processing Systems, 1992.Markdown
[Mozer and Das. "A Connectionist Symbol Manipulator That Discovers the Structure of Context-Free Languages." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/mozer1992neurips-connectionist/)BibTeX
@inproceedings{mozer1992neurips-connectionist,
title = {{A Connectionist Symbol Manipulator That Discovers the Structure of Context-Free Languages}},
author = {Mozer, Michael and Das, Sreerupa},
booktitle = {Neural Information Processing Systems},
year = {1992},
pages = {863-870},
url = {https://mlanthology.org/neurips/1992/mozer1992neurips-connectionist/}
}