COMS W4705: Natural Language Processing

[Main] | [General Information] | [Problem Sets]



Instructor: Michael Collins
Time & Location: This semester the class will be taught in a flipped classroom format: details are here.

TAs and Office Hours:
(All Office Hours held in CEPSR 7LW1, on the 7th floor of CEPSR)

Yufei Zhao [yz2605]: 10am-11.30am on Mondays
Wael Salloum (wael@ccls.columbia.edu): 5pm-6:30pm on Tuesdays
Yinghui Huang [yh2639]: 11am-12:30pm on Wednesdays
Joshua Wang [jw3123]: 2:30pm-4pm on Thursdays
Andrew James Mercer-Taylor [ajm2209]: 5:10pm-6:40pm on Fridays

Announcements:

October 8th, 2014: A reminder that the mid-term for the class is on Tuesday October 14th, 4.10-5.25pm, in 614 Schermerhorn. It is closed book, but you may take one letter-sized page of notes to the exam (you can use both sides of the page). The mid-term will cover all material up to and including week 6 (October 6th-10th), i.e., everything up to and including the "Lexicalized PCFGs" section of the class.

Past midterms for the class are here: fall 2011, fall 2012, fall 2013.


Lectures: Video lectures are on Coursera: once you have signed in to Coursera, follow this link.


Date Topics Video Lectures References Flipped Classroom Materials
Week 1 (Sept 1-5) Introduction to NLP,
Language Modeling (part 1)
Week 1 Coursera videos from Introduction (Part 1) (11:17) to Markov Processes (Part 2) (7:12) inclusive. Sections 1.1 and 1.2 of Notes on language modeling (required reading)
Questions, Solutions
Week 2 (Sept 8-12) Language Modeling (part 2) Week 1 Coursera videos from Trigram Language Models (9:40) to Summary (2:31) inclusive. Sections 1.3 and 1.4 of Notes on language modeling (required reading)
Questions, Solutions
Week 3 (Sept 15-19) Tagging, and Hidden Markov Models Week 2 Coursera videos from The tagging problem (10:01) to Summary (1:50) inclusive. Notes on tagging problems, and hidden Markov models (required reading)
Questions, Solutions
Week 4 (Sept 22-26) Parsing, and Context-free Grammars Week 3 - Parsing, and Context-free Grammars Coursera videos from Introduction (0:28) to Examples of Ambiguity (5:56) inclusive. Questions, Solutions
Week 5 (Sept 29-Oct 3) Probabilistic Context-free Grammars Week 3 - Probabilistic Context-Free Grammars (PCFGs) Coursera videos from Introduction (1:12) to The CKY Parsing Algorithm (Part 3) (10:07) inclusive. Notes on Probabilistic Context-Free Grammars (required reading)
Questions, Solutions
Week 6 (Oct 6-Oct 10) Lexicalized PCFGs All Week 4 Coursera videos, covering Weaknesses of PCFGs and Lexicalized PCFGs Notes on Lexicalized Probabilistic Context-Free Grammars (required reading)
Questions, Solutions
Week 7 (Oct 13-Oct 17) Mid-term Week Week 5 - Introduction to Machine Translation (MT) Coursera videos, covering Opening Comments (0:25) to Introduction to Statistical MT (12:31) inclusive. (Please watch these videos after the mid-term on Tuesday October 14th.) NOTE: there are no flipped classroom sections this week.
Week 8 (Oct 20-Oct 24) The IBM Translation Models Week 5 - The IBM Translation Models Coursera videos, covering Introduction (3:24) to Summary (1:48) inclusive. Notes on Statistical Machine Translation: IBM Models 1 and 2 (required reading)
Questions, Solutions
Week 9 (Oct 27-Oct 31) Phrase-Based Translation Models All Week 6 Coursera videos, covering Phrase-Based Translation Models and Decoding of Phrase-Based Translation Models. Notes on Phrase-Based Translation Models (required reading)
Questions, Solutions
Week 10 (Nov 5-Nov 11) Log-Linear Models All Week 7 Coursera videos, covering Log-Linear Models.

NOTE: Week 10 flipped classroom sections are Thursday Nov 6th, Friday Nov 7th, and Tuesday Nov 11th. There is no flipped classroom section on Tuesday Nov 4th, as this is a university holiday.

Notes on Log-Linear Models (required reading)
Week 11 (Nov 12-Nov 18) Log-Linear Models for Tagging, and Global Linear Models Week 8 - Log-Linear Models for Tagging (MEMMs) Coursera videos, and Week 9 - Global Linear Models (GLMs) Coursera videos.

NOTE: Week 11 flipped classroom sections are Thursday Nov 13th, Friday Nov 14th, and Tuesday Nov 18th.

Week 12 (Nov 19-Nov 25) Global Linear Models for Tagging Week 10 - GLMs for Tagging Coursera videos.

NOTE: Week 12 flipped classroom sections are Thursday Nov 20th, Friday Nov 21st, and Tuesday Nov 25th.

Week 13 (Dec 1-Dec 5) TBD TBD Coursera videos.

NOTE: Week 13 flipped classroom sections are Tuesday Dec 2nd, Thursday Dec 4th, Friday Dec 5th.