A Discriminative Model Corresponding to Hierarchical HMMs

@inproceedings{Sugiura2007ADM,
  title={A Discriminative Model Corresponding to Hierarchical HMMs},
  author={Takaaki Sugiura and Naoto Gotou and Akira Hayashi},
  booktitle={IDEAL},
  year={2007}
}
Hidden Markov Models (HMMs) are very popular generative models for sequence data. Recent work has, however, shown that on many tasks, Conditional Random Fields (CRFs), a type of discriminative model, perform better than HMMs. We propose Hierarchical Hidden Conditional Random Fields (HHCRFs), a discriminative model corresponding to hierarchical HMMs (HHMMs). HHCRFs model the conditional probability of the states at the upper levels given observations. The states at the lower levels are hidden… CONTINUE READING