|
CS 2731 / ISSP 2230 / INFSCI 2420: Introduction to Natural Language Processing (Fall 2019)
|
|
| Professor |
Dr. Diane Litman (5105 Sensq) |
| TA |
Ravneet Singh (5501 Sensq) |
| When & Where | Tuesday and Thursdays 1:00-2:15, SENSQ 5313 |
| Office Hours | Litman: Tu 4:30-5:30, Th 2:15-3:30, by appointment; Singh: M-Th 9-10:30 |
| Description | This course provides an introduction to the field of natural
language processing - the creation of programs
that can understand, generate, and learn languages used by
humans. It will expose students to applications such as
chatbots by means of
computational techniques including search algorithms, dynamic
programming, hidden markov models, probalistic context free
grammars, and machine learning algorithms.
Prerequisites: CS 1501 (algorithms) OR consent of the instructor Textbook: Speech and Language Processing (3rd edition online draft - free!) |
| Required Work (tentative) | Homeworks (35%): written and programming Exams (35%): midterm and final Group Course Project (25%): presentation and written report Supplemental Research Papers (5%): leading discussion and class participation Late Penalty: For assignments that may be accepted late, the penalty is 10% per day up to 5 days including Saturday, Sunday, and holidays. Assignments are due by 11:59pm. |
|
Date/Topic
|
Textbook Readings
|
Assignments and Other Readings |
|
| August 27 Introduction (pdf) |
Ch 1 | xkcd Humor (credits to E. Riloff for this and links below) |
|
|
I. Words
|
|||
| August 29 Text Normalization (pdf) |
Ch 2 (2.1-2.4) | Unix for Poets, pages 1-19
regular-expressions.info Humor: plurals, sentence tokenization |
|
| September 3, 5, 10 Language Modeling with N-Grams (pdf) |
Ch 3 (3.1-3.4) | Humor
Do at home: come prepared to discuss 9/5 HW1: assigned 9/5, due 9/24 9/4 NY Times: A breakthrough for AI (really NLP) technology |
|
| September 10, 12, 17 Part-of-Speech Tagging (pdf) |
Ch 8 (8.1-8.4.6) |
Humor
Schoolhouse Rock for Conjunctions Do at home: come prepared to decode "Fish sleep" using Viterbi on 9/17 |
|
|
II. Syntax (NOTE: The syntax chapter numbers are all off by one as they changed in the Octobe 2 textbook update)
|
|||
| September 17, 19 Constituency Grammars (pdf) |
Ch 11 (through 11.5) | Humor | |
| September 19, 24 Constituency Parsing (pdf) |
Ch 12 | Humor
Do at home: come prepared to show the result of parsing "The old dog the footsteps of the young" using the provided grammar on 9/24 |
|
| September 24, 26 Statistical Constituency Parsing (pdf) |
Ch 13 (13.1-13.5, 13.8) | HW2: assigned 9/26, due 10/10
Do at home: come prepared to derive parse trees for the provided sentence and grammar using CKY | |
|
III. Machine Learning
|
|||
| October 1, 3 Naive Bayes Classification (and Sentiment) (pdf) |
Ch 4 (through 4.8) | Humor
Do at home: come prepared to answer | |
| October 3, 8 Logistic Regression (pdf) |
Ch 5 (5.1-5.2; concepts in 5.3-5.7) | 9/26 NY Times: At Tech's Leading Edge, Worry about a Concentration of Power (evaluation of ML) | |
| October 8, 10, 15 Representation Learning (and Vector Semantics) (sparse vectors) (pdf) |
Ch 6 |
10/14 New Yorker: The Next Word: Where will predictive text take us? Midterm Review (pdf) |
|
| October 17 | Midterm Exam (closed book) | Through 9/26 class (statistical parsing). No makeups. | |
| October 22 Representation Learning (and Vector Semantics) (dense vectors) (pdf) |
Ch 6 |
HW3: assigned 10/22, due 11/5 Word2Vec Tutorial |
|
| October 24 Neural Nets (and Language Models) Guest Lecturer: Ravneet Singh |
Ch 7 | Introduction to Story Cloze Project (Corpus Paper, Shared Task Paper) | |
|
IV. Semantics
|
|||
| October 29, 31 Information Extraction (pdf) |
Ch 18 (18.1-2) | From word2vec to
BERT
(Bidirectional Encoder Representations from Transformers)
DRAFT project description |
|
| October 31, November 5 Word Senses and WordNet (pdf) |
Ch 19 | humor1,
humor2 |
|
| November 7, 12 Word Sense Disambiguation (pdf) |
Ch 19 | Midterm discussion Contextual Word Representations: A Contextual Introduction |
|
| November 14, 19 Semantic Role Labeling (pdf) |
Ch 20 | 11/11 NY Times: A.I. Systems Echo Biases They're Fed, Putting Scientists on Guard | |
|
V. Discourse and Applications
|
|||
| November 19, 21 Coreference Resolution (pdf) |
Ch 22 | ||
| December 3 Dialog Systems and Chatbots (pdf) |
Ch 26 | Final Exam Review (pdf) | |
| December 5 | Final Exam (closed book) | Everything since midterm (i.e., not cumulative). No makeups. | |
| December 10 cancelled due to double class on December 12 |
|||
| December 12 (from 1-3:50!!) | Project Presentations | Attendance required. | |
