Course Contents & Slides (Last update: 2001/11/07)

Natural Language Processing (#215021)

Text Books & References

(*) The textbook is to be decided since [1] has many minor
	but noisy errors as found in my last year's course --
(*) I am thinking of using [2] or [3] plus some of my own handouts
	as the replacement.

[1] Speech and Language Processing: An Introduction to Natural Language
	Processing, Computational Linguistics, and Speech Recognition,
	by Daniel Jurafsky & James H. Martin, Prentice Hall, 2000.

	Website: http://www.cs.colorado.edu/~martin/slp.html
	Errata: http://www.cs.colorado.edu/~martin/SLP/slp-errata.html (Local copy)

	Errata: http://www.cs.colorado.edu/~martin/SLP/New_Pages/pg455.pdf (Local copy)
		- Probabilistic CYK Algorithm

    [*] Slides & Addons:
	Preface
	Chapter 1: Introduction, Historical Review
	Chapter 2: Words, Regular Expression, Fast Matching (04/09)
	Chapter 2+: Chinese Words, Word Segmentation (03/27)
	Chapter 3: Morphology & Finite State Tranducers (04/10)
	Chapter 6: N-Gram (Model, Parameter Estimation & Smoothing) (04/17)
		Good-Tuning Smoothing & Backoff (04/17)
	Chapter 7: HMM (Hidden Markov Model) (slides: courtesy of Prof. Sheng-Wen Shih)
	Chapter 9: Context-Free Grammars (and a Simple Grammar for English) (06/05)
	Chapter 10: Parsing Algorithms -- (todo ...)
		Generic Chart Parsing (todo ...)
		CYK (todo ...)
		Earley (todo ...)
		Left-Corner Parsing (todo ...)
		LR Parser with Augmentation (todo ...)
	Chapter 12: PCFG, Trainable Grammars, and Lexicalization
	    [I] Trainable Grammars:
		1. Inside/Outside Probabilities
		2. Estimation of Rule Probabilities
		3. Finding Best Parse
	    [IIa] GPSM: PCFG enhanced with Context Sensitivity, Lexicalization and Normalization
	    [IIb] Lexicalized PCFG (todo)
	Todo ...

    [*] Figures of the book:
	Figs: http://www.cs.colorado.edu/~martin/SLP/Figures/PDF/slp-figs.tar.gz (Local copy)

	Other Figs: http://www.cs.colorado.edu/~martin/SLP/Figures/fixedtrees.tar (Local copy)

[2] Foundations of Statistical Natural Language Processing,
	by Christopher D. Manning and Hinrich Schutze,
	MIT Press, 1999. 

[3] Spoken Language Processing: A Guide to Theory, Algorithm, and System
	Development,
	by XueDong Huang, Alex Acero and Hsiao-Wen Hon,
	Prentice Hall PTR, Upper Saddle River, NJ 07458, USA, 2001.
	http://www.phptr.com

	(Ch. 1, Sec. 2.3-2.5, Ch. 3, Ch. 4, Sec. 5.8, Ch. 8, Ch. 11, Ch. 12,
	Ch. 13, Ch. 14, Sec. 17.3-17.5 will be particularly interesting
	for Statistical NLP.)

[4] Advanced NLP Issues ... (beyond algorithmic/application points of view ...)
	[1] Modeling Problems
		[1.1] Features
		[1.2] Dependency
	[2] Estimation Problems
		[2.1] Performance Metrics
		[2.2] Dicrimination
		[2.3] Robustness
		[2.4] Adaptive Training
		[2.5] Supervised vs. Unsupervised Training
			- Why and When

Conference Papers

[11] Chang, J.-S. , Y.-F. Luo and K.-Y. Su, "GPSM: A Generalized
Probabilistic Semantic Model for Ambiguity Resolution," Proceedings
of ACL-92, pp. 177--184, 30th Annual Meeting of the Association for
Computational Linguistics, University of Delaware, Newark, DE, USA,
28 June--2 July, 1992.


[13] Tung-Hui Chiang, Jing-Shin Chang, Ming-Yu Lin and Keh-Yih Su,
"Statistical Models for Word Segmentation and Unknown Word Resolution,"
Proceedings of ROCLING-V, ROC Computational Linguistics Conference
V, pp. 123--146, National Taiwan University, Taipei, Taiwan, ROC,
Sep. 18--20, 1992.
(PDF version)

Journals and Books

[6] Tung-Hui Chiang, Jing-Shin Chang, Ming-Yu Lin and Keh-Yih Su,
"Statistical Word Segmentation," in C.-R. Huang, K.-J. Chen and Benjamin
K. T'sou (eds.): Journal of Chinese Linguistics, Monograph Series
Number 9, Readings in Chinese Natural Language Processing, pp. 147-173.
University of California, Berkeley. 1996.

[7] K.-Y. Su, Tung-Hui Chiang, and Jing-Shin Chang, "An Overview
of Corpus-Based Statistics-Oriented (CBSO) Techniques for Natural
Language Processing," International Journal of Computational Linguistics
& Chinese Language Processing (CLCLP), vol. 1 no. 1, pp. 101--157,
August 1996.

[8] Yu-Ling Una Hsu, Jing-Shin Chang, and Keh-Yih Su, "Computational
Tools and Resources for Linguistics Studies," International
Journal of Computational Linguistics & Chinese Language Processing
(CLCLP), vol. 2, no. 1, pp. 1-39, 1997.




Miscellaneous

Su, K.-Y., T.-H. Chiang and J.-S. Chang, "Introduction to Corpus-based
Statistics-oriented (CBSO) Techniques,"  Pre-Conference Workshop
on Corpus-based NLP, ROC Computational Linguistics Conference VII,
National Tsing-Hua Univ., Taiwan, ROC.,  Aug. 1994.

	Part I: Introduction    (PDF/4) (PS/4) (PDF) (PS)
	Part II: Basic Concepts (PDF/4) (PS/4) (PDF) (PS)
	Part III: Techniques    (PDF/4) (PS/4) (PDF) (PS)
	Errata: Corrections to Part I-III TXT

"RFC 1922: Chinese Character Encoding for
Internet Messages," (2nd Rev.) was invited as a co-author of this RFC
document for my technical revisions on the ROC part of the ISO-2022
conformant encoding standard, aka ISO-2022-CN, (originated from the
Chinese Character Subworking Group of the I18N/L10N Working Group of
the Asian Pacific Networking Group, APNG-CC), March, 1995.
Reports related to RFC1922