CS 5890: Computational Linguistics
Instructor: Jugal Kalita
HW1: Counting words in the Open American National Corpus
Some general NLP tools
Mallet Statistical Natural Language Processing Toolkit for UMass,
Stanford NLP Toolkit
HW2: Parsing using CFG
Introduction to Natural Language Processing
: Chapters 2 and 3 of Jurafsky and Martin. We are also going to read the paper titled "
Unsupervised Learning of Morphology of a Natural Language", Computational Linguistics, 2001, by John Goldsmith
. It discusses morphology learning using the theory of Minimum Description Length.
N-Grams: Chapter 4 of Jurafsky and Martin
: Chapter 5 of Jurafsky and Martin. We also read the paper titled "
A Simple Rule-based Part of Speech Tagger" by Eric Brill
, 3rd ACL Conference on Applied Computational Linguistics, 1992.
Hidden Markov Models
: Chapter 6 of Jurafsky and Martin. Theuse of HMMs in POS tagging.We looked at Chapter 12 of
Statistical Methods in Bioinformatics by Ewens and Grant,
Chapter 12 titled "Hidden Markov Models", Sections 12.1 and Section 12.2.
Formal Grammars of English:
Chapter 12 of Jurafsky and Martin
Syntactic Parsing: Chapter 13 of Jurafsky and Martin