Hierarchical Hidden Conditional Random Fields for Information Extraction
Hidden Markov Models (HMMs) are very popular generative models for time series data. Recent work, however, has shown that for many tasks Conditional Random Fields (CRFs), a type of discriminative model, perform better than HMMs. Information extraction is the task of automatically extracting instances of specified classes or relations from text. A method for information extraction using Hierarchical Hidden Markov Models (HHMMs) has already been proposed. HHMMs, a generalization of HMMs, are generative models with a hierarchical state structure. In previous research, we developed the Hierarchical Hidden Conditional Random Field (HHCRF), a discriminative model corresponding to HHMMs. In this paper, we propose information extraction using HHCRFs, and then compare the performance of HHMMs and HHCRFs through an experiment.
KeywordsHide Markov Model Information Extraction Viterbi Algorithm Discriminative Model Test Sentence
Unable to display preview. Download preview PDF.
- 1.Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proc. 18th Int. Conf. Machine Learning (2001)Google Scholar
- 2.Fine, S., Singer, Y., Tishby, N.: The hierarchical hidden Markov model: Analysis and applications. Machine Learning 32(1) (1998)Google Scholar
- 3.Murphy, K., Paskin, M.: Linear time inference in hierarchical HMMs. In: Advances in Neural Information Processing Systems, vol. 14 (2001)Google Scholar
- 6.Skounakis, M., Craven, M., Ray, S.: Hierarchical hidden Markov models for information extraction. In: Proc. 18th Int. Joint Conf. Artificial Intelligence (2003)Google Scholar
- 7.Huang, C., Darwiche, A.: Inference in belief networks: A procedural guide. Int. J. of Approximate Reasoning 15(3) (1996)Google Scholar
- 9.Cestnik, B.: Estimating probabilities. In: Proc. 9th European Conf. Artificial Intelligence (1990)Google Scholar