Natural Language Processing I

CSCI 657/490-B8

Spring 2023

Last updated Thu. 2/2/2023

Back to Reva Freedman's home page

Course Information

• Syllabus
• Departmental academic integrity policy
• Simplified Python style guide
• PEP 8 Python style guide

Sections below to be updated

Python Resources

Python reference

• Python official web site
• Python package repository Google is sometimes more useful.
• Python documentation for version 3.9.2 (inc. tutorial and HOWTOs)

Introductory Python

• Python for Everybody Absolute beginners should go through chapter 7.
• Bernd Klein's Python course

NLP Resources

Textbooks

• Jurafsky and Martin textbook web site

Papers

• ACL Anthology: Digital Archive of Research Papers in Computational Linguistics

Statistics

• Choosing the correct statistical test (UCLA)

NLP Software

NLTK

• NLTK website
• Book

Java software

• LingPipe: Java Libraries for NLP

Linguistics

• Ethnologue: Languages of the World

Artificial Intelligence

• AI Topics (from AAAI)

Programming Resources

Unicode

• Unicode general category values

Unix information

• MobaXterm
• Important Unix commands
• Most common Emacs commands

Old notes

What makes NLP hard

• Language variation: Language Files 10.10
• Surface form vs. meaning (the duck sentences)
• Types of ambiguities
• Even knowing what's a word is hard
• More types of ambiguity
• Humans have problems too: Garden path sentences

Morphology

• English morphology
• Evidence for human two-level processing
• Stemming without a lexicon (Porter)

Spelling correction

• Kernighan's COLING '90 paper
• Bayes' theorem for ASR

Discourse

• Pragmatics: Intention vs. form

Preliminary form

• CFGs
• Greenberg's universals
• Language change over time
• Meaning