CS G224: Natural Language Processing

Readings and On-Line Resources for CS G224 Natural Language Processing
Spring 2006, Prof. Hafner

Contents:
I. Class notes (MS Word format)
Week 2 Class notes
Week 4 Class notes
Week 5 Class notes
Week 6 Class notes
Week 7 Class notes
Week 8 Class notes
Week 9 Class notes
Week 10 Class Notes
Week 11 Class notes
Week 12 Class notes
Week 13 Class notes

II. Assigned and Supplementary Readings

III. Local Resources

IV. Web Resources

Assigned Readings:

Updated Chapter on POS Tagging from the Web page associated with our textbook.
Chart Parser tutorial from NLTK website (Sections 1 and 2)
Health Dialog Systems for Patients and Consumers, by Bickmore, T. and Giorgino, T. (to appear in Journal of Biomedical Informatics).

Supplementary Readings:
Week 1

Building a Large Annotated Corpus of English: The Penn Treebank explains how and why the Brown tagset was simplified to produce the smaller Penn Treebank tagset

Week 3

More references for student teams to look at:
MUC:

Design of the MUC-6 Evaluation (the last MUC) by Ralph Grishman and Beth Sundheim
Overview of Results of the MUC-6 Evaluation (the last MUC) by MUC organizer Beth Sundheim
The Automatic Content Extraction (ACE) Program Tasks, Data, and Evaluation (a paper describing a new program continuing the MUC concept of content extraction aiming toward concept-level NL understanding).

SENSEVAL: 2 short papers on SENSEVAL-3 by Kenneth C. Litkowski

The UC Berkeley FrameNet project -- relevant to both Lexical Resources/Ontology and to SENSEVAL

The FrameNet Web site
Three short papers describing FrameNet by Charles Fillmore and colleagues at UC Berkeley

TREC

Overview of TREC-2004 by Ellen M. Voorhees

Local Resources (requires Unix login ID/password)

Slides/Outlines of student talks presented on January 25, 2006

NL Corpus talk - Outline (pdf)
NL Corpus talk - Slides (also pdf)
Lexicons and Ontologies talk (Powerpoint)
NL tools talk - Slides (Powerpoint)
MUC talk (Powerpoint)
TREC talk - Slides (Powerpoint)
SENSEVAL tall - Slides (Powerpoint)

Web resources

SLP Web Page (our text book)
UCREL - University Centre for Computer Corpus Research on Language (Lancaster University, UK)
BNC - The British National Corpus, Oxford University
WordNet
MUC
TREC
SENSEVAL
Stanford University NLP Annotated List of Resources
NLTK - Natural Language Toolkit (select "Documentation" menu item)
Linguistic Data Consortium - University of Pennsylvania

Last updated 14 April 2006