Department of Mathematicscoretheory
NATURAL LANGUAGE PROCESSING
DSE 4402
Syllabus
- 01Knowledge in Speech and Language Processing
- 02Ambiguity
- 03Models and Algorithm
- 04Regular Expressions
- 05Finite State Automata
- 06Words And Transducers: Survey of English Morphology
- 07Finite-State Morphological Parsing
- 08Building a Finite-State Lexicon
- 09FSTs for Morphological Parsing
- 10Lexicon-Free FSTs
- 11Words and Sentence tokenization: Normalizing Text
- 12Segmentation
- 13Probabilistic Models of Pronunciation and Spelling
- 14Detecting and Correcting Spelling Errors
- 15Noisy Channel Model
- 16Minimum Edit Distance
- 17N-Grams: Unsmoothed N-Grams
- 18Smoothing
- 19Interpolation and Backoff
- 20English Word Classes: Tag-sets for English
- 21Part-of-Speech Tagging
- 22Formal Grammars of English: Context Free Grammars
- 23Grammar Rules
- 24TreeBank
- 25Dependency Grammar
- 26Parsing with Context Free Grammars
- 27Dynamic Programming Parsing
- 28CKY algorithm
- 29Statistical Parsing
- 30NLP using NLTK SDL
References
- Daniel Jurafsky & James H. Martin, Speech and Language Processing, (2e), Pearson, 2009.
- Steven Bird, Ewan Klein and Edward Loper, Natural Language Processing with Python, First Edition, O'Reilly Media, 2009.
- J.E.Hopcroft, R.Motwani & J.D.Ullman, Introduction to Automata Theory Languages, and Computation, (3rd Edition), 2006, Pearson Education.
Credits Structure
3Lecture
0Tutorial
0Practical
3Total