Paper: Hierarchical Non-Emitting Markov Models

ACL ID P97-1049
Title Hierarchical Non-Emitting Markov Models
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1997

We describe a simple variant of the inter- polated Markov model with non-emitting state transitions and prove that it is strictly more powerful than any Markov model. Empirical results demonstrate that the non-emitting model outperforms the inter- polated model on the Brown corpus and on the Wall Street Journal under a wide range of experimental conditions. The non- emitting model is also much less prone to overtraining.