This is the schedule of topics for Computational Linguistics I (CMSC/LING 723), Fall 2007.
Readings are from the second edition of Dan Jurafsky and James Martin (to be published in 2007), "Speech and Language Processing: An Introduction to Natural Language Processing, Speech Recognition, and Computational Linguistics." Although this edition is not yet available for purchase, you may click here for the updated chapters.
| Class | Topic | Readings | Lecture Notes | Assignments |
|---|---|---|---|---|
| Aug 29 | Administrivia, semester plan; overview of NLP; Intro to MT (Bonnie) | New Ch 1 | Lecture Notes 1 | -- |
| Sep 5 | MT continued (Bonnie) | New Ch 24.1, 24.2, 24.9 (will become Ch 25 in final edition) | Lecture Notes 2 | Assignment 1 (no-credit ice-breaker; Due Sept 19) |
| Sep 12 | Introduction to Python and NLTK (Nitin) | NLTK Book (Chapters 1 and 2); Python Beginners' Guide (includes resources for both programmers and non-programmers); ACM article on Getting Started on NLP with Python | Lecture Notes 3 | -- |
| Sep 19 | Finite State Automata, Regular Expressions, Intro to Morphology (Bonnie) | New Ch 2; Start New Ch 3 | Lecture Notes 4 | Assignment 2 (Due Oct 3) |
| Sep 26 | Morphology and FSTs (Bonnie) | Finish New Ch 3; New Ch 5 (Sections 5.1-5.4) | Lecture Notes 5 | -- |
| Oct 3 | Hidden Markov models (HMMs), Expectation-Maximization and HMM training (Nitin) | New Ch 5 (Section 5.5), New Ch 6; See also the Wikipedia entry on dynamic programming | HMM handout Lecture Notes 6 |
Assignment 3 (Due Oct 17) |
| Oct 10 | Context-free grammars (CFG), linguistic phenomena, complexity (Bonnie) | New Ch 12 (Sections 12.1-12.6), Parts of New Ch 15. | Lecture Notes 7 | -- |
| Oct 17 | Context-free parsing: CYK, Earley (Bonnie) | New Ch 13; See also Wikipedia: CYK algorithm and Shieber et al. (1995) sections 1-3 | Lecture Notes 8 | Take home midterm handed out. (Due Oct 31) |
| Oct 24 | Attend Two NLP Colloquia | 10/10/2007 11-12, AVW 2120 (Speech): Mary Harper abstract, slides; 10/17/2007 11-12, KIM 1105 (NLP Apps): Chris Dyer, Jimmy Lin abstract and slides; 10/31/2007 11-12, AVW 2460 (Language Acquisition): C. Anton Rytting abstract |
-- | -- |
| Oct 31 | N-gram language models (Nitin) | New Ch 4: sections 4.1-4.7, 4.9.1 | Lecture Notes 9 | Assignment 4 (Due Nov 14) |
| Nov 7 | Lexical semantics (Bonnie) | New Ch 19 | Lecture Notes 10 | -- |
| Nov 14 | Semantics | New Ch 17 | Lecture Notes 11 and Earley Parser revisited | Assignment 5 (Due Nov 28) |
| Nov 21 | Noisy Channel Model and Transformation-Based Learning THIS MATERIAL HAS MOVED TO DEC 5 | New Ch 5.5 (intro and 5.5.1); New Ch 9.1; New Ch 5.6 | Lecture Notes 12 | -- |
| Nov 28 | Tree-adjoining grammars and Combinatorial Categorial Grammars (Nitin from Bonnie's notes) |
TAG: Pages 1-13 and 27-33 (Section 8) of Aravind Joshi and Yves Schabes, Tree-Adjoining
Grammars, in Handbook of Formal Languages, G. Rozenberg and
A. Salomaa (eds.), Vol. 3, Springer, Berlin, New York, 1997, 69-124; see
also additional pointers to important TAG-related papers in these notes for a seminar lecture given by Yuqing Guo in 2006/2007.
CCG: New Ch 12 (Section 12.7); Mark Steedman, Categorial Grammar (tutorial overview), Lingua, 90:221--258, 1993; and Shieber et al. (1995) section 4. |
Lecture Notes 13 | -- |
| Dec 5 | Finish Semantics and Notes from Lecture 12; Use of Paraphrase in MT; Exam Review (Bonnie, Nitin) | Review sheet and Nitin's Paraphrase article. | Study!! | Take home final handed out Dec 12th, Due Dec 19th |