| James Pustejovsky | Volen 258, jamesp, x62709 |
| José Castaño | Volen 110, jcastano, x62743 |
| Marc Verhagen | Volen 110, marc, x62745 |
| Anna Rumshisky (TA) | Volen 256, arum, x62726 |
| Ben Wellner (TI) | Volen 110, wellner, x62743 |
This course provides a fundamental understanding of the problems in natural language processing by computers, and the theory and practice of the current computational linguistic systems. Of interest to students of artificial intelligence, algorithms, and the computational processes of comprehension and understanding.
| Topic | Readings | Assignments | Staff | |
|---|---|---|---|---|
| W, Jan 18 | Intro to CL | Python Tutorial, not due | JC+MV | |
| M, Jan 23 | Some history | SALP 1 | JP | |
| W, Jan 25 | Tokenization | SALP 2, 3 | Tokenizer, due 2/6 | MV |
| M, Jan 30 | POS tagging | SALP 6, 7, 8 | JC | |
| W, Feb 1 | POS tagging | JC | ||
| M, Feb 6 | Chunking | Tagging/Chunking, due 2/17 | JC | |
| W, Feb 8 | Parsing | SALP 9, 10, 11, 12 | JC | |
| M, Feb 13 | Parsing | JC | ||
| W, Feb 15 | Parsing | JC | ||
| M, Feb 20 | no class | |||
| W, Feb 22 | no class | |||
| M, Feb 27 | Entity Recognition | Parsing Exercise, due 3/10 | MV | |
| W, Mar 1 | Entity Recognition | slides | Entity Recognition, due 3/20 | MV |
| M, Mar 6 | Semantics: Representing Meaning | SALP 14, 15 | JP | |
| W, Mar 8 | Seminar | |||
| M, Mar 13 | Semantics: Compositionality & GL | slides, SALP 16 | JP | |
| W, Mar 15 | Semantics: Types and Coercion | Final Project, due 5/1 | JP | |
| M, Mar 20 | Learning | JC | ||
| W, Mar 22 | Learning: MaxEnt | slides | BW | |
| M, Mar 27 | Learning: CRFs | slides | BW | |
| W, Mar 29 | TARSQI | slides, http://tarsqi.org | MV | |
| M Apr 3 | Information Retrieval | slides, SALP 17.3 | MV | |
| W, Apr 5 | Information Retrieval | slides | MV | |
| M, Apr 10 | Information Retrieval | slides | Problem Set, due 4/24 | MV |
| W, Apr 12 | Question Answering | MV | ||
| M, Apr 17 | no class | |||
| W, Apr 19 | no class | |||
| M, Apr 24 | Presentations | schedule | class | |
| W, Apr 26 | Presentations | class | ||
| M, May 1 | TBD |
Jurafsky, D. and Martin, J. H. Speech and Language Processing: an introduction to natural language processing, computational linguistics, and speech recognition. Upper Saddle River, NJ: Prentice Hall. 2000. (On order at the Science Library and available at BC, MIT, and Tufts libraries.)
Allen, James. Natural Language Understanding, Redwood City, CA: Benjamin/Cummings Publishing Company, Inc., 1995. (Science Library Reserve: QA76.7 .A44 1995)
Manning, Christopher, and Schutze, Hinrich. Foundations of Statistical Natural Language Processing, Cambridge, MA: MIT Press, 1999. (Science Library Reserve: P98.5.S83 M36 1999)
Lutz, Mark. Learning Python, Beijing/Sebastopol, CA: O'Reilly, 1999. (Science Library Reserve: QA76.73.P98 l877 1999)
Fehily, Chris. Python: Visual Quickstart Guide. CA: Peachpit, 2002.
Assignments are due electronically by 11:59 pm on the date given. Assignments will be charged a 5% late-fee per 24 hour day. They won't be accepted a week after the due date. This policy will be strictly adhered to.
All assignments, except for the final project, are indivual work. You are allowed to discuss your borrow proze and code from other sources as long as you acknowledge it. You will be graded on your own contributions as well as how you incorporate existing code. The invidual assignments count towards the total as follows:
python tutorial 0% tokenizer 10% tagging/chunking 5% parsing 10% entity recognition 15% problem set 15% final project 45%
Code should run on Python version 2.2.3, which will be made available on the machines in the Berry patch. If you use another version, please test it on 2.2.3 before you turn it in. We won't accept code that doesn't run.
To submit electronically, send the assignment to cs114@cs.brandeis.edu.
There is no midterm or final exam, your course grade will be determined by your assignments.Computational Linguistics
Morphology