For our May meeting Kevin Scannell, Professor of Mathematics and Computer Science at Saint Louis University will be discussing Natural Language Processing.
We'll have food and drink available. Room 5206 @ 4444 Forest Park Avenue.
Many of the advances in machine translation and speech recognition
over the last twenty years are due to the introduction of statistical
techniques. I will explain two fundamental ideas that drive a lot of
the work in the field of Natural Language Processing: (1) the
"noisy-channel" model and (2) the Expectation Maximization (EM)
algorithm. I'll give plenty of concrete examples showing how these
ideas are used in practice.