Introduction to Natural Language Processing (600.465)Words and the Company They Keep

Table of Contents

Introduction to Natural Language Processing (600.465)Words and the Company They Keep

Motivation

Collocations

Association and Co-occurence;Terms

Collocations of Special Interest

Further Notions

How to Find Collocations?

Frequency

Hypothesis Testing

t test (Student’s t test)

t test on words

Pearson’s Chi-square test

Pointwise Mutual Information

Email: hajic@cs.jhu.edu

Home Page: http://www.cs.jhu.edu/~hajic/courses/cs465/syllabus.html