ICS 482: Natural Language Processing

​

ICS 482: Natural Language Processing

 
Course Information
Class/Laboratory Schedule: 

Three 50 minutes lectures per week (3-0-3)

Designation: 
 Elective Course
Course Level: 
 Undergraduate
Prerequisites
Prerequisite(s) by Topic: 
  • Functions, Relations and Sets
  • Basic Logic
  • Basics Algorithmic Analysis
  • Algorithmic Strategies
Prerequisite Courses: 
Senior Standing
Catalog Description: 

This course examines a range of issues concerning computer systems that can process human languages. Among the issues to be discussed are morphological and syntactic processing, semantic interpretation, discourse processing and knowledge representation

Textbook(s): 

Jurafsky, D. and J. H. Martin: Speech and Language Processing. Prentice-Hall. 2009.

Reference(s) and Other Material: 
  • Manning, C. D. and H. Schütze: Foundations of Statistical Natural Language Processing. The MIT Press. 1999. ISBN 0-262-13360-1.
Course Outcomes: 

After completion of this course, the student shall be able to:

  • Identify areas where Natural Language processing (NLP) could be used.
  • Have a fundamental knowledge of the basic elements of natural language technology, such as grammatical formalisms, parsing methods, and text understanding.
  • Understand how meaning-representations for natural language sentences can be computed (first order predicate calculus, semantic net).
  • Understand how discourse interpretation could solve many problems that NLP systems face between sentences.
  • Have practical experience of natural language systems development (be able to construct simple tokenizer, parser).
  • Identify and analyze a natural language processing problem with respect to the requirements of a specific application, and motivate and implement a solution.
  • Explore web resources, choose a topic, study it, prepare and deliver a presentation.
Topics Covered: 
  • Words, Morphology And Finite State Transducers
  • Regular Expressions.
  • Ngram
  • Syntax, Context-free grammars & parsing
  • Probabilistic Context free Grammars
  • Representing Meaning
  • Semantic Analysis
  • Lexical Semantics
  • Discourse
  • NLP Application: Machine Translation, NLP & the web​