Speech and Natural Language Processing, Autumn 2007, Sudeshna Sarkar

Speech & Natural Language Processing

CS 60057

Autumn 2007

Instructor : Sudeshna Sarkar
Teaching Assistant: Sandipan Dandapat, Sunandan

Time Table :

Wednesday	11:30-12:25
Thursday	10:30-11:25
Friday	8:30-9:25

Textbook:

Speech and Language Processing : by Jurafsky & Martin

Reference Book:

Statistical Natural Language Processing: by Manning

Course Information :

The course will have assigments, a midterm, a final examination and a substantial project. The weightage for the various components are tentatively as follows:
Assignments and Projects: 40 %

Midterm : 25 %
Final : 35 %

NLTK
NLTK, the Natural Language Toolkit, is a suite of program modules, data sets and tutorials supporting research and teaching in computational linguistics and natural language processing. NLTK is free software, released under an open source license.
In this course we will use the nltk_lite package. The latest release is NLTK 0.8 available from the Natural Language Toolkit website.

Assignments

Assignment 1 : set on 3rd August 2006. Due on 10th August 2007.
Assignment 2 : set on 25th August 2006. Due on 30th August 2007.

Past Exams

NLP midterm Autumn 2006
NLP endterm Autumn 2006

NLP Lectures

Date	Lecture Material
1. 25 July 2007	Introduction
2 26 July 2007	Ambiguity
3. 27 July 2007	Morphology-1
4. 1st August 2007	Morphology-2
5. 2nd August 2007	Words
6. 3rd August 2007	N-grams
7. 8th August 2007	N-grams continued
8, 9th August 2007	POS tagging
9. 9th Aug 2007	POS tagging
10. 16th Aug 2007	HMM, POS tagging
11. 17th August 2007	HMM, Noisy channel model
12. 22nd Aug 2007	Parsing-1
13. 23rd Aug 2007	Parsing-2
14. 24th Aug 2007	Parsing-3 MT-1
15. 31st August	MT-2
16. 5th Sep 2007	Statistical MT
17. 6th Sep 2007	Stat MT-2
18. 7th Sep 2007	Parsing with Features
19. Semantics	Semantics
20. Semantics	Semantics
21. Lexical Semantics	Lexical Semantics
Information Extraction	Information Extraction Web Information Extraction ICML Tutorial ACL Tutorial
Question Answering	Question Answering
Opinion Mining	Opinion Mining
Paraphrasing	Paraphrasing
Summarization	Summarization