Artificial Neural Networks for Repairing Language

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{WW98b,
 	 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},
 	 journal = {}
 	 editors = {}
 	 number = {}
 	 volume = {}
 	 pages = {117--123},
 	 year = {1998},
 	 month = {Sep},
 	 publisher = {}
 	 doi = {}
 	 url = {http://www2.informatik.uni-hamburg.de/wtm/publications/1998/WW98/neurap95repair.pdf},
 }