Linguistics 645
Advanced Natural Language Processing (NLP)
Autumn 2009

Course goals

In recent years, statistical methods have become the standard in the field of natural language processing (NLP). This course gives an introduction to statistical models and machine learning paradigms in NLP. Such methods are helpful for reaching wide coverage, reducing ambiguity, automatic learning, increasing robustness, etc.

In this course, we will cover basic notions in probability and information theory, focusing on the concepts needed for NLP. Then we will discuss (Hidden) Markov Models, exemplified by an approach to POS tagging. The following sessions will be dedicated to probabilistic approaches to parsing, focusing on probabilistic context-free grammars.

Additionally, we will cover semantic role labeling, word sense disambiguation, and (if time) statistical alignment methods and their use in machine translation. We will be focusing on statistical methods in the context of particular tasks, but the methods we discuss are applicable to a range of tasks in NLP. Thus, this course provides an essential platform for further work in NLP.


Some details

Meeting time: MW, 1:00-2:15pm
Classroom: Lindley Hall (LH) 030
Credits: 3
Course prerequisites: Computation and Linguistic Analysis (L545) or permission of instructor.
Some programming experience is expected.

Instructor: Markus Dickinson
Office: Memorial Hall (MM) 317
Phone: 856-2535
E-mail: md7 ...AT... illinoisindiana.edu (remove our neighbor state)

Office hours:
T 12-1pm
F 10-11am
  or by appointment


Textbook:

Course requirements:

Academic Misconduct:

Academic misconduct is not allowed in this course. The Indiana University Code of Student Rights, Responsibilities, and Conduct (http://dsa.indiana.edu/Code/) defines academic misconduct as ``any activity that tends to undermine the academic integrity of the institution . . . Academic misconduct may involve human, hard-copy, or electronic resources . . . Academic misconduct includes, but is not limited to . . . cheating, fabrication, plagiarism, interference, violation of course rules, and facilitating academic misconduct'' (II. G.1-6).

Students with Disabilities:

Students who need an accommodation based on the impact of a disability should contact me to arrange an appointment as soon as possible to discuss the course format, to anticipate needs, and to explore potential accommodations.

I rely on Disability Services for Students for assistance in verifying the need for accommodations and developing accommodation strategies. Students who have not previously contacted Disability Services are encouraged to do so (812-855-7578; http://www.indiana.edu/~iubdss/).


(Tentative) Schedule:

Month Date Topic Reading Assignments
Aug. 31 Intro to class (.pdf, .2x3pdf) MS, ch. 1  
Sep. 2 Probability Theory (.pdf, .2x3pdf) (handout) MS, 2.1  
  7 Probability Theory KS, 1.1-1.4  
  9 Collocations (.pdf, .2x3pdf) MS, ch. 5 HW1 due
  14 Information Theory (.pdf, .2x3pdf) MS, 2.2; KS, 2.2  
  16 Corpora and Linguistic Annotation (.pdf, .2x3pdf) MS, ch. 3, 4 HW2 due
  21 FSAs (.pdf, .2x3pdf); Markov Chains \& Models (.pdf, .2x3pdf) MS, 9.1; KS, 2.1.1-2.1.3  
  23 N-gram POS tagging (.pdf, .2x3pdf)   HW3 due
28 Practical POS tagging (.pdf, .2x3pdf)    
  30 Smoothing (.pdf, .2x3pdf) JM, 4.5; MS, 6.2 HW4 due
Oct. 5 Hidden Markov Models (.pdf, .2x3pdf) MS, 9.2-9.3; KS, 2.1.4  
  7 Calculating P(O) (.pdf, .2x3pdf) MS, 9.3.1; KS, 2.1.5  
  12 Finding the Optimal State Sequence MS, 9.3.2; KS, 2.1.6  
  14 Parameter Estimation (.pdf, .2x3pdf) MS, 9.3.3; KS, 2.1.7 HW5 due
  19 CYK parsing (.pdf, .2x3pdf) JM, 13-13.4.1  
  21 Practical Parsing I   HW6 due
  26 Probabilistic Context-Free Grammars (.pdf, .2x3pdf) MS, 11.1-11.3.3  
  28 PCFGs (.pdf, .2x3pdf) JM, 14.2, 14.4-14.5 HW7 due
Nov. 2 Probabilistic Parsing (.pdf, .2x3pdf) + Evaluation (.pdf, .2x3pdf) MS, ch. 12  
  4 Practical Parsing II (.pdf, .2x3pdf, files)    
  9 Estimating PCFGs (.pdf, .2x3pdf) MS, 11.3.4-11.4  
  11 Estimating PCFGs   HW8 due
  16 Beyond PCFGs (.pdf, .2x3pdf) MS, ch. 8, Charniak and Johnson (2005); McClosky et al. (2006)  
  18 Beyond PCFGs Petrov et al. (2006); Klein and Manning (2003) HW9 due
  23 PP attachment Merlo and Ferrer (2006)  
  25 NO CLASS: Thanksgiving    
  30 Semantic role labeling (SRL) (.pdf, .2x3pdf) Márquez et al. (2008)  
Dec. 2 SRL Toutanova et al. (2008) or Pradhan et al. (2008) HW10 due
  7 Word Sense Disambiguation MS, ch. 7  
  9 Statistical Machine Translation (SMT) MS, ch. 13  
  17 Final HW/Project due   Final HW due

Disclaimer

This syllabus is subject to change and likely will change. All important changes will be made in writing, with ample time for adjustment.


Bibliography

Charniak, Eugene and Mark Johnson (2005).
Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking.
In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05). Ann Arbor, Michigan: Association for Computational Linguistics, pp. 173-180.
urlhttp://www.aclweb.org/anthology/P05-1022.

Klein, Dan and Christopher D. Manning (2003).
Accurate Unlexicalized Parsing.
In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics. Sapporo, Japan: Association for Computational Linguistics, pp. 423-430.
http://www.aclweb.org/anthology/P03-1054.

Márquez, Lluis, Xavier Carreras, Kenneth C. Litkowski and Suzanne Stevenson (2008).
Special Issue Introduction: Semantic Role Labeling: An Introduction to the Special Issue.
Computational Linguistics 34(2), 145-159.
http://aclweb.org/anthology-new/J/J08/J08-2001.pdf.

McClosky, David, Eugene Charniak and Mark Johnson (2006).
Reranking and Self-Training for Parser Adaptation.
In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics. Sydney, Australia: Association for Computational Linguistics, pp. 337-344.
http://www.aclweb.org/anthology/P06-1043.

Merlo, Paola and Eva Esteve Ferrer (2006).
The Notion of Argument in Prepositional Phrase Attachment.
Computational Linguistics 32(3), 341-377.
http://aclweb.org/anthology-new/J/J06/J06-3002.pdf.

Petrov, Slav, Leon Barrett, Romain Thibaux and Dan Klein (2006).
Learning Accurate, Compact, and Interpretable Tree Annotation.
In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics. Sydney, Australia: Association for Computational Linguistics, pp. 433-440.
http://www.aclweb.org/anthology/P06-1055.

Pradhan, Sameer S., Wayne Ward and James H. Martin (2008).
Towards Robust Semantic Role Labeling.
Computational Linguistics 34(2), 289-310.
http://aclweb.org/anthology-new/J/J08/J08-2006.pdf.

Toutanova, Kristina, Aria Haghighi and Christopher D. Manning (2008).
A Global Joint Model for Semantic Role Labeling.
Computational Linguistics 34(2), 166-191.
http://aclweb.org/anthology-new/J/J08/J08-2002.pdf.