MITRE TDT-2000 SEGMENTATION SYSTEM

We present t he design and d evelopment of a Hidden Markov Model for the division o f news broadcasts into story segments. Model t opology, and the textual features used, are discussed, together with the non-parametric estimation techniques that were employed for obtaining estimates for both transition and observation p robabilities. Visualization methods developed for the analysis of system performance are also presented.

[1]  J. R. Koehler,et al.  Modern Applied Statistics with S-Plus. , 1996 .

[2]  M. Wand.  Local Regression and Likelihood , 2001 .

[3]  Ronald Rosenfeld,et al.  Trigger-based language models: a maximum entropy approach , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Guohua Pan,et al.  Local Regression and Likelihood , 1999, Technometrics.

[5]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[6]  David W. Scott.  The New S Language , 1990 .

[7]  Trevor Hastie,et al.  Statistical Models in S , 1991 .