Artificial Neural Networks for Repairing Language

Volker Weber , Stefan Wermter
Proceedings of the 8th International Conference on Neural Networks and their Applications, - Sep 1998
Associated documents :  
Spontaneous language contains many discontinuities caused by unusual order, false starts, repairs, repetitions, pauses, etc. Since data-driven artificial neural networks possess an inherent fault tolerance we use this property for dealing with such forms of “sequential noise”. We describe an approach for a flat syntactic and semantic interpretation of ill-formed utterances in spontaneous dialogs using symbolic methods for communication and simple known mappings as well as connectionist methods for unknown mappings. As an example for fault-tolerant flat analysis we describe the use of our syntactic and semantic representation for recovering from repairs in our hybrid approach using real–world spontaneous dialog utterances.

 

@InProceedings{WW98, 
 	 author =  {Weber, Volker and Wermter, Stefan},  
 	 title = {Artificial Neural Networks for Repairing Language}, 
 	 booktitle = {Proceedings of the 8th International Conference on Neural Networks and their Applications},
 	 editors = {},
 	 number = {},
 	 volume = {},
 	 pages = {},
 	 year = {1998},
 	 month = {Sep},
 	 publisher = {},
 	 doi = {}, 
 }