Artificial Neural Networks for Repairing Language
Proceedings of the 8th International Conference on Neural Networks and their Applications,
pages 117--123,
- Sep 1998
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
realworld 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},
journal = {None},
editors = {}
number = {}
volume = {}
pages = {117--123},
year = {1998},
month = {Sep},
publisher = {}
doi = {}
}