This is the schedule of topics for Computational Linguistics II, Spring 2005.
Readings are from Christopher D. Manning and Hinrich Schuetze, Foundations of Statistical Natural Language Processing, unless otherwise specified. The "other" column has optional links pointing either to material you should already know (but might want to review) or to related material you might be interested in.
| Class | Topic | Readings* | Assignments | Other |
|---|---|---|---|---|
| Jan 26 | Course administrivia, semester plan; preliminaries |
Ch 1, 2.1.[1-9] | Do the Jan 26 and Feb 2 readings. | |
| Feb 2 | Words and lexical association |
Ch 5 | Assignment 1 (due 4pm, Feb 9) | Dunning (1993), Bland and Altman (1995) |
| Feb 9 | Information theory and N-gram models |
Ch 6, Ch 2.2 | Assignment 2 (due 4pm, Feb 16) | |
| Feb 16 | Smoothing, Hidden Markov models |
Ch 6, 9-10 | ||
| Feb 23 | HMMs continued; Probabilistic grammars |
Ch 3, 11, Abney (1996) | Assignment 3 (due 4pm, Mar 2) | Pereira (2000) |
| Mar 2 | Probabilistic grammars, continued |
Ch 11 | Assignment 4 (due 4pm, Mar 9) | Resubmits of Assignment 2 accepted until 4pm today |
| Mar 9 | Guest Lecture: David Chiang Probabilistic parsing and treebanks |
Ch 11, 12 | Study! | Guidance for studying |
| Mar 16 | Midterm Exam |
none | ||
| Mar 23 | Spring Break |
none | Relax! | |
| Mar 30 | Lexical acquisition |
Ch 8 (exc 8.5) | Assignment 5 (due 4pm, Apr 13) | |
| Apr 6 | Guest lecture: Christof Monz Similarity and similarity-based methods |
Ch 8.5, 15.{1,2,4} | Lee? Lin? Resnik? | |
| Apr 13 | Word sense disambiguation |
Ch 7 | Assignment 6 (due 4pm, April 20) | Ch 16? Maxent? |
| Apr 20 | WSD and NLP applications |
Resnik (2005) book chapter draft | ||
| Apr 27 | The Web as a corpus |
Kilgarriff and Grefenstette (2003); Keller and Lapata (2003); Resnik and Elkiss (DRAFT) | Assignment 7 (extra credit, due 4pm May 4) | WebExp software for Web-based psycholinguistics; Linguist's Search Engine; Michalcea (2004) |
| May 4 | Parallel text and its uses |
Ch 13 | Assignment 8 (due 4pm May 11) | Resnik (2004); Mihalcea and Pedersen (2003) |
| May 11 | Computational psycholinguistics |
Jurafsky and Martin (2000), Sections 12.5 (Human Parsing) and 13.4 (Complexity and Human Processing); Jurafsky (2003) (except Sections 2.1, 2.2, 2.5, 2.6, 3.1, 3.5, 3.6) . | Study for final! | Lewis (2000), Resnik (1992), Hale syllabus |
| May 19 | Final Exam, 4-6:30pm, CSCI 2107 |
Officially cumulative but with a strong (at least 80%) emphasis on material after the midterm. | Relax! | Guidance for studying |