An Introduction to Stochastic Attribute-Value Grammars
by Rob Malouf, Miles Osborne
Publisher: ESSLLI 2001
Number of pages: 159
This one-week course will provide an introduction to the maximum entropy principle and the construction of maximum entropy models for natural language processing. Through a combination of lectures and, as local computing facilities permit, hands-on lab exercises, students will investigate the implementation of maximum entropy models for attribute-value grammars, including such topics as ambiguity identification, feature selection, and model training and evaluation.
Home page url
Download or read it online for free here:
by Igor Boshakov, Alexander Gelbukh
The book focuses on the basic set of ideas and facts from the fundamental science necessary for the creation of intelligent language processing tools, without going deeply into the details of specific algorithms or toy systems.
by Shuly Wintner - ESSLLI
This text is a mild introduction to Formal Language Theory for students with little or no background in formal systems. The motivation is Natural Language Processing, and the presentation is geared towards NLP applications, with extensive examples.
by A. L. Berger, S. A. Della Pietra, V. J. Della Pietra - Association for Computational Linguistics
The authors describe a method for statistical modeling based on maximum entropy. They present a maximum-likelihood approach for automatically constructing maximum entropy models and describe how to implement this approach efficiently.
by Roger Levy - University of California, San Diego
A book on the topic of using probabilistic models in scientific work on language ranging from experimental data analysis to corpus work to cognitive modeling. The intended audience is graduate students in linguistics, psychology and computer science.