CS 224N / Ling 284  —  Natural Language Processing

Home · Syllabus · Textbook and Readings · Grading · Piazza · OpenEdX · Calendar


Calendar


Mon Tue Wed Thu Fri
Sep 21 Sep 22
Lecture 1: Introduction
Sep 23 Sep 24
Lecture 2: Word Alignment Models for Statistical MT PA1 out 		Sep 25
Sep 28 Sep 29
Lecture 3: Machine Translation: Word Alignment, Parallel Corpora, Decoding, Evaluation 		Sept 30 Oct 1
Lecture 4: Modern MT Systems (Phrase-based, Syntactic) 		Oct 2
Oct 5 Oct 6
Lecture 5: N-Grams, Final Project Discussion 		Oct 7 Oct 8 PA2 out
Lecture 6: Syntax and parsing PA1 due 		Oct 9
Oct 12 Oct 13
Lecture 7: Competitive Grammar Writing I 		Oct 14 Oct 15
Lecture 8: Competitive Grammar Writing II 		Oct 16
Oct 19 Oct 20
Lecture 9: Dependency Parsing Final project proposal due 		Oct 21 Oct 22 PA2 due
Lecture 10: Coreference Resolution PA3 out 		Oct 23
Oct 26 Oct 27
Lecture 11: Coreference Resolution II / Classifiers 		Oct 28 Oct 29
Lecture 12: Softmax / MaxEnt (Sequence) Classifiers 		Oct 30
Nov 2 Nov 3
Lecture 13: Sequence Classifiers for POS & NER / Deep Learning for NLP: Motivations 		Nov 4 Nov 5 PA3 due
Lecture 14: Deep Learning for NLP: Word Representations & NER PA4 out 		Nov 6
Nov 9
Nov 10
Lecture 15: Deep Learning for NLP: Strategy and Tree Recursive Neural Networks 		Nov 11 Nov 12
Lecture 16: Deep Learning for NLP: Recurrent Neural Networks 		Nov 13
Nov 16
Nov 17
Lecture 17: Computational Semantics 		Nov 18 Nov 19
Lecture 18: Computational Semantics 		Nov 20
Nov 23 Nov 24
Thanksgiving
Nov 25 Nov 26
Thanksgiving
Nov 27
Nov 30
Dec 1
Final project presentations 		Dec 2 Dec 3
Final project presentations 		Dec 4

PA 4 due: Dec 4.
Final project report due: Dec 6.

Syllabus

Lecture 1
Tue
9/22/15		 Course Introduction and Administration. Overview of NLP. Statistical Machine Translation.

Lecture Slides: (1-up) (6-up)

Required:
  • If your knowledge of probability theory is limited, please read M&S 2.0-2.1.7. If that's too condensed, read the probability chapter of an intro statistics textbook, e.g. Rice, Mathematical Statistics and Data Analysis, ch. 1.
Optional:
Lecture 2
Thu
9/24/15		 Word Alignment Models for Statistical MT

Assignments:
  • PA1 (Word Alignment and MT System) Out. (Find it on OpenEdX under Courseware.)
 Lecture Slides: (1-up) (6-up)

Tutorial reading: Background: Advanced:
Lecture 3
Tue
9/29/15		 Machine Translation: Word Alignment, Parallel Corpora, Decoding, Evaluation

Lecture Slides: (1-up) (6-up)

Required:
  • J&M chapter 25
Tutorial reading: Optional:
Lecture 4
Thu
10/1/15		 Modern MT Systems (Phrase-based, Syntactic)

Lecture Slides: (1-up) (6-up)

Optional:
Lecture 5
Tue
10/6/15		 N-Grams, Final Project Discussion

Lecture Slides: (1-up) (6-up)

Required: Resources: Optional:
Lecture 6
Thu
10/8/15		 Syntax and parsing

Lecture Slides: (1-up) (6-up)

Assignments:
  • PA1 due
  • PA2 (CYK-Parser) out
 Required:
  • Week 3 Parsing Videos
  • J&M ch. 13, secs. 13.0-13.3.
Background:
  • J&M ch. 12 (or M&S ch. 3). This is especially if you haven't done any linguistics courses, but even if you have, there's useful information on treebanks and part-of-speech tag sets used in NLP.
Lecture 7
Tue
10/13/15		 Competitive Grammar Writing I

Lecture Slides: (pdf)
Instructions: (pdf)

Required:
  • Week 4 Parsing Videos
  • J&M sec 13.4
Background:
Lecture 8
Thu
10/15/15		 Competitive Grammar Writing II

Required:
  • Week 4 Parsing Videos
Optional:
Lecture 9
Tue
10/20/15		 Dependency Parsing

Lecture Slides: (1-up) (6-up)

Assignments:
  • Final Project Proposal Due.
Lecture 10
Thu
10/22/15		 Coreference Resolution

Lecture Slides: (1-up) (6-up)

Assignments:
  • PA2 Due
  • PA3 (Coreference System) out

Required:
  • J&M 21.3-21.8 (or all of Chapter 21 if you wish!)
Optional:
Lecture 11
Tue
10/27/15		 Coreference Resolution II

Lecture Slides: (1-up) (6-up)
Intro to feature-based classifiers: (1-up) (6-up)
Lecture 12
Thu
10/29/15		 Softmax / MaxEnt (Sequence) Classifiers

Lecture Slides: (1-up) (6-up)

Optional:
Lecture 13
Tue
11/3/15		 Sequence Classifiers for POS & NER / Deep Learning for NLP: Motivations

Lecture Slides:
  • Maxent models continuation:(1-up) (6-up)
  • Intro to deep learning and word representations: (1-up) (6-up)
Lecture 14
Thu
11/5/15		 Deep Learning for NLP: Word representations & NER

Lecture Slides: (1-up) (6-up)

Assignments:
  • PA3 Due
  • PA4 (Deep Learning Sequence Model or Dependency Parsing) out
Lecture 15
Tue
11/10/15		 Deep Learning for NLP: Strategy & Tree Recursive Neural Networks

Lecture Slides: (1-up) (6-up)

Optional reading (from easiest to hardest!):
Lecture 16
Thu
11/12/15		 Deep Learning for NLP: Recurrent Neural Networks

Lecture Slides: (1-up) (6-up)
Lecture 17
Tue
11/17/15		 Computational Semantics

Lecture Slides: [1-up] [6-up]

Background links: [Background on knowledge navigator] [SHRDLU] [Google app 2015]
Lecture 18
Thu
11/19/15		 Computational Semantics

Lecture Slides: first part (1-up) (6-up); second part (1-up).

Required:



Lecture Slides: third part (1-up).
  Thanksgiving Break
Lecture 19
Tue
12/1/15		 Final project presentations

Schedule

Lecture 20
Tue
12/3/15		 Final project presentations

Schedule

 

Site design by Bill MacCartney