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:

Chandra Shankar Kappera - Monday 9:00am to 10:30am, computer science TA room

Zehao Song - Tuesday 10:00am to 11:30am, computer science TA room

Kartikeya Upasani - Wednesday 11:00am to 12:30pm, computer science TA room


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

Lectures: Video lectures are all available by logging in to Courseworks 2.

Date Topics Video Lectures References Flipped Classroom Materials
Week 1 (Sept 4th-8th) Introduction to NLP,
Language Modeling (part 1) (Slides)
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 11th-15th) Language Modeling (part 2) (Slides same as Week 1) 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. 18th-22nd) Tagging, and Hidden Markov Models (Slides) 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. 25th-29th) Parsing, and Context-free Grammars (Slides) Week 3 - Parsing, and Context-free Grammars Coursera videos from Introduction (0:28) to Examples of Ambiguity (5:56) inclusive. Questions, Solutions
Week 5 (Oct 2nd-6th) Probabilistic Context-free Grammars (Slides) 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 9th-13th) Lexicalized PCFGs (Slides part 1), (Slides part 2) 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 16th-20th) Mid-term Note: no flipped classrooms this week, but extra office hours on Oct 16th.
Week 8 (Oct 23rd-27th) Log-Linear Models (Slides) All Week 7 Coursera videos, covering Log-Linear Models.

Notes on Log-Linear Models (required reading)
Questions, Solutions
Week 9 (Oct 30th-Nov 3rd) Log-Linear Models for Tagging (Slides), and Global Linear Models (Slides) Week 8 - Log-Linear Models for Tagging (MEMMs) Coursera videos, and Week 9 - Global Linear Models (GLMs) Coursera videos.

Notes on MEMMs (Log-Linear Tagging Models) (required reading)
Questions, Solutions
Week 10 (Nov 6th-10th) Feedforward Neural Networks (Slides) Section 22 videos in Courseworks.

Notes on Feedforward Neural Networks (required reading)
Questions, Solutions
Week 11 (Nov 13th-17th) Computational Graphs, and Backpropagation (Slides) Section 23 videos in Courseworks.

Notes on Computational Graphs, and Backpropagation (required reading)
Questions, Solutions
Week 12 (Nov 27th-Dec 1st) Word Embeddings in Feedforward Networks; Tagging and Dependency Parsing using Feedforward Networks (Slides) Section 24 videos in Courseworks.