ECE 467: Natural Language Processing

• Instructor Info
• Textbook
• Grading
• Schedule

Instructor Info

Instructor: Carl Sable
e-mail: carl.sable@cooper.edu (but please submit assignments to CarlSable.Cooper@gmail.com)
Office: Room 614

Textbook

"Speech and Language Processing, 3rd Edition" (draft, in-progress, on-line only)
by Daniel Jurafsky and James H. Martin

Grading

Assignments will be posted here when they are assigned.

• Text Categorization Project: 25%
  Click here for the corpora for the text categorization project
  Project #1 is due before midnight the night of Thursday, March 10
• Parsing Project: 25%
  Click here for a sample grammar expressed as a general CFG
  Click here for a weakly equivalent grammar in CNF
  Click here for my Python 3 program that converts a CFG to CNF
  (NOTE: I changed the file extension to .txt to avoid server issues, you should change it back to .py)
  Project #2 is due before midnight the night of Thursday, April 7
• Individual or Group Open Ended Programming Project: 25%
  Project ideas and group members should be sent to be before midnight the night of Tuesday, May 3
  Project #3 is due before midnight the night of Tuesday, May 10
  Projects will be presented in class either Wednesday, May 11 or Thursday, May 12
• 3 Problem Sets: 25% (total)
  Click here for probem set #1
  Problem set #1 is due by the start of class on Thursday, February 24
  Click here for probem set #2
  Problem set #2 is due by the start of class on Wednesday, April 6
  Click here for probem set #3
  Problem set #3 is due by the start of class on Wednesday, May 11

Schedule

Note 1: All dates and topics which have not yet occurred are tentative!

Note 2: All below references to chapters and sections of the Jurafsky and Martin textbook are based on a draft version of the 3rd edition dated December 29, 2021.

• Wednesday, January 19
  Topic 1: Course Introduction (Slides)
• Thursday, January 20
  Topic 2: Tokenization, Words, and Morphology (Slides)
  Suggested reading: Chapter 2 of Jurafsky and Martin
• Wednesday, January 26
  Topic 2 (continued)
• Thursday, January 27
  Topic 3: N-grams and Conventional Language Models (Slides)
  Suggested reading: Chapter 3 of Jurafsky and Martin
• Wednesday, February 2
  Topic 4: Part-of-Speech Tagging (Slides)
  Suggested reading: Chapter 8 of Jurafsky and Martin
• Thursday, February 3
  Topic 4 (continued)
• Thursday, February 10
  Topic 5: Vector Space Models, Information Retrieval, and Text Categorization (Slides)
  Suggested reading: Chapter 4, Sections 6.3 - 6.5, and Section 23.1 of Jurafsky and Martin
• Wednesday, February 16
  Topic 5 (continued)
• Thursday, February 17
  Topic 5 (continued)
  Project #1 assigned

• Wednesday, February 23
  Topic 6: Phrase-Structure Grammars and Dependency Grammars (Slides)
  Suggested reading: Chapter 12 and Sections 14.1 - 14.3 of Jurafsky and Martin
• Thursday, February 24
  Topic 6 (continued)
  Topic 7: Natural Languages and Psycholinguistics (Slides)
• Wednesday, March 2
  Topic 7 (continued)
• Thursday, March 3
  Topic 8: Parsing (Slides)
  Suggested reading: Sections 13.1 - 13.2 and Appendix C of Jurafsky and Martin
• Wednesday, March 9
  Topic 8 (continued)
• Thursday, March 10
  Topic 8 (continued)
  Project #2 assigned
  Topic 9: First-Order Logic and Semantics (Slides)
  Suggested reading: Chapter 15 of Jurafsky and Martin
• Wednesday, March 23
  Topic 9 (continued)
• Thursday, March 24 (first half)
  Topic 9 (continued)

• Thursday, March 24 (second half)
  Topic 10: Feedforward Neural Networks (Slides)
  Suggested reading: Sections 7.1 - 7.4 and Section 7.6 of Jurafsky and Martin
• Wednesday, March 30
  Topic 10 (continued)
• Thursday, March 31
  Topic 10 (continued)
  Topic 11: Word Embeddings, Neural Language Models, and Word2vec (Slides)
  Suggested reading: Sections 6.8 - 6.10, Section 7.5, and Section 7.7 of Jurafsky and Martin
• Wednesday, April 6
  Topic 11 (continued)
• Thursday, April 7
  Topic 11 (continued)
  Topic 12: Recurrent Neural Networks and LSTMs (Slides)
  Suggested reading: Sections 9.1 - 9.6 of Jurafsky and Martin
• Wednesday, April 13
  Topic 12 (continued)
• Thursday, April 14
  Topic 12 (continued)
  Topic 13: Encoder-Decoder Models, Attention, and Machine Translation (Slides)
  Suggested reading: Chapter 10 of Jurafsky and Martin
• Wednesday, April 20
  Project #3 assigned
  Topic 13 (continued)
• Thursday, April 21
  Topic 13 (continued)
  Topic 14: Advanced Topics: Character and Subword Embeddings; Question Answering Systems; Transformers; Contextual Word Embeddings (e.g., ELMo, BERT, GPT); Ethics and NLP (Slides)
  Suggested reading: Section 2.4.3, Section 6.8.3, Chapter 23, Section 9.7, Section 10.6, Sections 11.1 - 11.3, Section 4.10, Section 6.11, Section 10.9, Section 11.6, and Section 24.6.1 of Jurafsky and Martin
• Wednesday, April 27
  Topic 14 (continued)
• Thursday, April 28
  Topic 14 (continued)
• Wednesday, May 4
  Topic 14 (continued)
• Wednessday, May 11
  Presentations
• Thursday, May 12
  Presentations