For complex natural language understanding systems with a large number of statistically confusable but semantically different formal commands, there are many difficulties in performing an accurate translation of a user input into a formal command in a single step. This paper addresses scalability issues in natural language understanding, and describes a method for performing the translation in a hierarchical manner. The hierarchical method improves the system accuracy, reduces the computational complexity of the translation, provides additional numerical robustness during training and decoding, and permits a more efficient packaging of the components of the natural language understanding system.
Cite as: Ramaswamy, G.N., Kleindienst, J. (2000) Hierarchical feature-based translation for scalable natural language understanding. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 3, 506-509, doi: 10.21437/ICSLP.2000-583
@inproceedings{ramaswamy00_icslp,
author={Ganesh N. Ramaswamy and Jan Kleindienst},
title={{Hierarchical feature-based translation for scalable natural language understanding}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 3, 506-509},
doi={10.21437/ICSLP.2000-583}
}