Learning Incremental Case Assignments Based on Modular Connectionist Knowledge Sources

This paper describes techniques for designing appropriate hybrid connectionist architectures in real world language environments. We argue that for dealing with arbitrary real world corpora we can identify the underlying constraints for a task but the integration and interaction of these constraints cannot be predicted in general for arbitrary unrestricted language bases. Therefore flexible automatic learning and incremental parallel integration of various constraints are particularly important for scaling up in real world environments. As a particular example we will focus on a hybrid connectionist architecture for semantic case assignment to support automatic learning and incremental parallel constraint integration.

@InProceedings{WP94,
 	 author =  {Wermter, Stefan and Peters, Ulf},
 	 title = {Learning Incremental Case Assignments Based on Modular Connectionist Knowledge Sources},
 	 booktitle = {Proceedings of the World Congress on Neural Networks},
 	 journal = {}
 	 editors = {}
 	 number = {}
 	 volume = {}
 	 pages = {538--543},
 	 year = {1994},
 	 month = {Jan},
 	 publisher = {}
 	 doi = {}
 }