Fourth European Conference on Speech Communication and Technology

Madrid, Spain
September 18-21, 1995

Integrating Heuristic Preferences Into A Neural Understanding System

Adelaide Stevenur (1,2), Patrick Gallinari (1)

(1) LAFORIA IBP-UA CNRS1095, Université Pierre et Marie Curie, Paris, France
(2) Institute Of Systems Science, National University of Singapore, Singapore

We have been developing a neural natural language understanding system oriented towards the extraction of information relevant to a task. We have implemented a version of this system for an air travel reservation task. We have studied systems that map input sequences to output sequences, and conceived a recurrent neural system for conceptual decoding. Robustness, learnability and flexible integration of different information sources are some of the attractive features of our model. Training Neural Networks to capture long-term dependencies remains an important challenge. We present results of our attempts to capture global constraints between noncontiguous semantic patterns. We propose a new system that combines our connectionist model and an N-Best like module for higher-level post segmental treatment.

Full Paper

Bibliographic reference.  Stevenur, Adelaide / Gallinari, Patrick (1995): "Integrating heuristic preferences into a neural understanding system", In EUROSPEECH-1995, 1215-1218.