Hierarchical Non-Emitting Markov Models
| dc.creator | Ristad, Eric Sven | |
| dc.creator | Thomas, Robert G. | |
| dc.date | 1998-01-14 | |
| dc.date | 1998-01-20 | |
| dc.date.accessioned | 2026-07-07T02:36:11Z | |
| dc.date.available | 2026-07-07T02:36:11Z | |
| dc.description | We describe a simple variant of the interpolated Markov model with non-emitting state transitions and prove that it is strictly more powerful than any Markov model. More importantly, the non-emitting model outperforms the classic interpolated model on the natural language texts under a wide range of experimental conditions, with only a modest increase in computational requirements. The non-emitting model is also much less prone to overfitting. Keywords: Markov model, interpolated Markov model, hidden Markov model, mixture modeling, non-emitting state transitions, state-conditional interpolation, statistical language model, discrete time series, Brown corpus, Wall Street Journal. | |
| dc.description | http://www.cs.princeton.edu/~ristad/papers/pu-544-97.ps.gz | |
| dc.identifier | https://arxiv.org/abs/cmp-lg/9801001 | |
| dc.identifier | http://arxiv.org/abs/cmp-lg/9801001 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/15822 | |
| dc.subject | Computation and Language | |
| dc.title | Hierarchical Non-Emitting Markov Models | |
| dc.type | text |