An Accelerated Introduction to Statistical Language Modeling

Monday, October 30, 2000 - 11:00am - 12:00pm
Keller 3-180
Roni Rosenfeld (Carnegie-Mellon University)
tatistical Language Models estimate the distribution of various natural language phenomena for the purpose of speech recognition and other language technologies. Since the first significant model was proposed in 1980, many attempts have been made to improve the state of the art. I will review those, point to a few promising directions, and argue for a Bayesian approach to integration of linguistic theories with data.

The talk will be loosely based on the survey paper:

Two decades of Statistical Language Modeling: Where Do We Go From Here?, Roni Rosenfeld, Proceedings of the IEEE 88(8), August 2000 pdf (98KB) postscript (113KB).

that was mailed to the workshop participants ahead of the workshop. However, the talk will be considerably more technical, and will be specifically designed to rapidly introduce statisticians and mathematicians to the field.