CSC 9010: Special Topic
Natural Language Processing
Spring, 2005, Thurs, 6:15-9:00
Mendel 156
Dr. Mary-Angela Papalaskari
Department of Computing Sciences, Villanova
Email: map@villanova.edu
Phone: (610) 519-7307
Office Hours: M,W,Th 5PM-6PM and by appointment
Dr. Paula Matuszek
Principal Computing Scientist, GlaxoSmithKline
Email: Paula_A_Matuszek@gsk.com
Phone: (610) 270-6851
Office Hours: after class and by appointment
Description:
Does your software need to understand English?
Natural language processing (NLP) has been a research topic of interest
to computer scientists for many decades; it is one of the capabilities
clearly required by the test for artificial intelligence proposed by
Alan Turing in 1950. It is only in the past 10 years or so, however,
that this research has matured enough to have significant practical
application. The web has given NLP work a substantial impetus; it both
increases by orders of magnitude the text material available
electronically and highlights how impossible it is to deal with all of
the material manually. NLP techniques now underlie
- Effective search and document retrieval
- Speech processing for automated voice systems
- Information extraction of names, entities, and facts from
documents
- Document categorizing and clustering
- Automated translation
and a variety of other functions.
Course Objectives:
This course gives an overview of NLP, establishing a basic grounding in
morphology, syntax, semantics, and pragmatics. Both knowledge-based and
statistical approaches are explored. Practical applications, such as
text mining will be considered and used to motivate some of the more
theoretical material. Topics to be covered in more depth will be
determined in part by the interests of the class. Hands-on exercises
using Python and the Natural Language Toolkit
(http://nltk.sourceforge.net) reinforce the material; student
presentations give participants the opportunity to look in more depth
at an area of interest.
Textbook:
SPEECH and LANGUAGE PROCESSING: An Introduction to Natural Language
Processing, Computational Linguistics, and Speech Recognition, by
Daniel Jurafsky and James H. Martin
Prerequisite: Design and
Analysis of Algorithms or permission of instructor.
Questions: email Dr. Papalaskari at map@villanova.edu or Dr.
Matuszek at paula.a.matuszek@gsk.com
Syllabus
Requirements and Grading
Academic Integrity
Student Questionnaire