Natural Language Processing

Spring 2006
Tuesdays, 9:10 ~12:00 AM
Instructor:
Berlin Chen

 

Topic List and Schedule

2/21
 
Course Overview & Introduction
 
HW1: Chinese Input System
- List of Base Syllables
- Lexicon
- Text
2/28
 
Break
 
3/7
 
Mathematical Foundations*
 
 
3/14
 
Linguistic Essentials
 
 
3/21
 
N-gram Language Modeling*
 
 
3/28
 
Part-of-Speech Tagging & Named-Entity Extraction
 
HW2: Trace of TBL Tagging
 
4/4
 
Break
 
4/11
 
Part-of-Speech Tagging & Named-Entity Extraction
 
4/18
 
Midterm
 
4/25
 
Collocations*
 
5/2
 
Parsing with Context-Free Grammars
 
HW3: HMM-based Tagging
 
5/9
 
Parsing with Context-Free Grammars
 
HW4: Natural Language Understanding, Chapter 3, Exercise  8 & 9 (p.78)
5/16
 
Word Sense Disambiguation*
 
5/23
 
Break (TechSEE)
 
5/30
 
Paper Survey*
Probabilistic Context-Free Grammars
6/6
 
Statistical Sentence Alignment and Machine Translation
 
6/23
 
    Final Deadline for HW submissions
 

Textbook: 

1. D. Jurafsky and J. H. Martin, Speech and Language Processing, Prentice-Hall, 2000.
2. C. Manning and H. Schutze, Foundations of Statistical Natural Language Processing, MIT Press, 1999.

References:
 
Books:

1. J. Allen, Natural Language Understanding, Benjamin/Cummings Publishing Co, 1995.
2. X. Huang, A. Acero, H. Hon, Spoken Language Processing, Prentice Hall, 2001.

  Papers:

 Corpora:

1. The Association for Computational Linguistics and Chinese Language Processing

Grading:
     1. Midterm or Final: 25%
     2. Homework: 50%
     3. Presentation: 15%
     4. Attendance/Other: 10%