Document Type
Syllabus
Description
This course is designed to introduce students to the current statistical techniques for the automatic analysis of natural (human) language data. It develops an in-depth understanding of both the algorithms available for the processing of linguistic information and the underlying computational properties of natural languages. Potential topics include language modeling, finite state models, stochastic grammars, latent semantic analysis, log-linear models in natural language processing. We will explore how these core techniques can be applied to user applications such as information extraction, question answering, automatic speech recognition, statistical machine translation.
Publication Date
Fall 2006
College
College of Engineering and Computer Science
Department
Computer Science
Course Number
CS 790-02
Comments
Section 02 of CS 790-02: Statistical Natural Language Processing: Methods and Models