Jim's
Tutorials

Spring 2012
course
navigation

2012-01-21

Update on nlp-class.org

Class start has been postponed to February 2012. Specific date to follow.
Because of the delay, I will not be following the class for now.

In the meantime

Elias is working on his Final Plan Application.
Found these to replace nlp-class.org:
I also like these:
These are probably my favourite:

Topics covered by Uni. of Toronto course

Schedule

(from website source)
WeekSubjectsLecture slidesAssigned reading
1
(9, 11 January)
  • Introduction
  • Language models and corpora
Manning and Schutze: sections 1.3--1.4.2 and sections 6.0--6.2.1
2
(16, 18 January)
  • N-grams, Zipf, and smoothing
  • Part-of-Speech (PoS) tagging
Manning and Schutze: sections 1.4.3, 6.2.2 and sections 6.3--6.3.3
3
(23, 25 January)
  • Entropy
  • Statistical significance and decision trees
Manning and Schutze: section 2.2 and sections 5.3--5.3.2
4 (2 February)
  • Hidden Markov models
Manning and Schutze: sections 9.2--9.4.1 and rabiner.pdf
5 (9 February)
  • Hidden Markov models
  • Statistical machine translation
Manning and Schutze: sections 13.0 and 13.2
6 (16 February)
  • Statistical machine translation
Manning and Schutze: sections 13.1.2, 13.1.3, and 13.3
23 February
  • N/A: reading week
  • N/A
7 (2 March)
  • Statistical machine translation
  • Acoustics and speech perception
8 (9 March)
  • Acoustics and speech production
  • Automatic speech recognition
Manning and Schutze: Section 14.2.2
9 (16 March)
  • Automatic speech recognition
  • Review
10 (23 March)
  • Speech synthesis
  • Miscellaneous classification
11 (30 March)
  • Information retrieval
12 (6 April)
  • Summarization
Lecture notes will be available around the beginning of the weeks.

Topics covered by U. Texas course

UTexas order

  1. n-gram language models
  2. Part Of Speech Tagging and Sequence Labeling
  3. Syntactic parsing
  4. Semanti Analysis
  5. Information Extraction (IE)
  6. Machine Translation (MT)

What I want to do

  1. Language Models and Corpora (Toronto – refresher from last semester)
  2. Entropy (Toronto)
  3. Statistical Significance and Decision Trees (Toronto)
  4. Conditional Random Fields (Texas)
  5. Syntactic Parsing (Texas)
  6. Statistical Parsing (Texas)
  7. Word Sense Disambiguation (Texas)
    1. http://en.wikipedia.org/wiki/Word-sense_disambiguation
    2. http://www.aclweb.org/anthology-new/J/J98/#1000
  8. Information Extraction (Texas)
    1. Information Retrieval (Toronto)
  9. Statistical Machine Translation (Toronto)
    1. Machine Translation (Texas)
  10. Text categorization (Texas)
  11. Text clustering (Texas)
If time allows:
  1. Acoustics and speech production (Toronto)
  2. Automatic speech recognition (Toronto)
  3. Speech synthesis (Toronto)

Texts

Jims says

For what it's worth, I have a friend at MIT who's in the thick of this project :
http://cs.marlboro.edu/ courses/ spring2012/jims_tutorials/ elias/ 2012-01-21
last modified Tuesday February 7 2012 9:01 pm EST