Hybrid Neural and Symbolic Language Processing

In this paper we outline hybrid approaches to artificial neural network-based natural language processing. We suggest various types of symbolic/connectionist integration for language processing: connectionist structure architectures, hybrid transfer architectures, hybrid processing architectures. Furthermore, we focus particularly on loosely coupled, tightly coupled, and fully integrated hybrid processing architectures. We argue that the hybrid approach to artificial neural network based language processing has a lot of potential to overcome the gap between a neural level and a symbolic conceptual level.

@InProceedings{Wer98b,
 	 author =  {Wermter, Stefan},
 	 title = {Hybrid Neural and Symbolic Language Processing},
 	 booktitle = {Proceedings of Interdisziplinäres Kolleg},
 	 journal = {None},
 	 editors = {}
 	 number = {}
 	 volume = {}
 	 pages = {139-148},
 	 year = {1998},
 	 month = {Jan},
 	 publisher = {}
 	 doi = {}
 }