Linguistics 439/539
Statistical Natural Language Processing

Handouts:

Matlab files:

thenoun.m: "the + noun" example
twodie.m: expectation and variance for two dice
binom.m: binomial distribution
wordlengthbrown.m: calculates word lengths for the Brown corpus
diceEntropy.m: computes entropy for a die with from 1 to 20 sides
fourSided.m: computes the entropy for a single die with 4 sides where one of the sides has increasing probability from 0 to 1.
myLog.m: log function where log(0) = 0
mutinfex.m: mutual information
engEntropy.m: entropy of English
nGramApprox.m: N-gram approximation for English
zipf.m: Zipfian distribution for English
persuasion.m: N-grams in Persuasion
lapmh.m: Laplace demo
mleele.m: more N-grams in Persuasion
efficient.m: Coding efficiency demo
unseen.m: Sparse data demo
laws.m: Laplace & Lidstone demo
gtanal.m: Good-Turing implemented
gtdemo.m: Good-Turing demo
sli.m: Simple Linear Interpolation demo
tagambig.m: Frequency of word types with multiple tags in Brown
dumbtagger.m: Dumb tagging demo
welshxml.m: Quick and dirty code for parsing Welsh National Assembly xml files
kmeansdemo.m: K-means demo
varycolor.m: RGB color spectrum generator (needed for kmeansdemo.m)
coinsEM.m: Simplified Expectation-maximization demo
vectorspace.m: Vector Space demo
poisson.m: Poisson distribution
poissonfigure.m: Plotting Poisson distributions
snlp5.zip: Sample answer to assignment #5
twopoisson.m: Plotting a two-poisson distribution
kmix.m: Plotting a K-mixture distribution
leastsquares.m: Least squares demo
bim.m: Binary Independence Model demo
chsq.m: Chi-square function for two samples
dectreedemo.m: Decision tree demo
maxentdemo.m: Maxent demo
perceptrondemo.m: Perceptron demo
neuralnetdemo.m: Neural net demo

Linguistics 439/539Statistical Natural Language Processing

Handouts:

Matlab files:

Links:

Linguistics 439/539
Statistical Natural Language Processing