08/26 Lecture 01
What is NLP? What will you learn in this class? How will we teach this class?
Required reading: this and this, plus Ch.1 (2nd Ed)
Optional reading: Python tutorial (sec. 1-5)
08/28 Lecture 02
Tokenization and Morphology
Tokenization, finite-state transducers, the structure of words
Required reading: Ch. 2
Optional Reading: TBA
08/28–09/04 Quiz 1
09/02 Lecture 03
Probabilistic modeling in NLP
Review of basic probability. How do we apply these ideas to NLP? N-gram language models
Required reading: Ch. 3
Optional reading: MS, Ch. 2
09/04 Lecture 04
Text Classification with Naive Bayes
Introduction to binary classification with probabilistic models.
Required reading: Ch. 4
Optional Reading: TBA
09/04–09/25 HW1
09/09 Lecture 05
Logistic Regression
Introduction to conditional probabilistic models for classification
Required reading: Ch. 5
Optional Reading: TBA
09/11 Lecture 06
Vector Semantics and Embeddings
Representing words as vectors (with or without neural models)
Required reading: Ch. 6
Optional Reading: TBA
09/11–09/18 Quiz 2
09/16 Lecture 07
Feedforward Neural Nets
Basic neural nets for classification and language modeling
Required reading: Ch. 7
Optional Reading: TBA
09/18 Lecture 08
Convolutional Neural Nets for NLP
Another neural architecture for (text) classification
Required Reading: TBA
09/18–09/25 Quiz 3
09/23 Lecture 09
Part-of-Speech Tagging
What are parts-of-speech? Introduction to HMMs
Required Reading: Ch. 8
Optional Reading: TBA
09/25 Lecture 10
More on POS Tagging
More on HMMs (Viterbi algorithm)
Required Reading: Ch. 8
Optional Reading: TBA
09/25–10/16 HW2
09/30 Lecture 11
Recurrent Nets for Sequence Modeling
Introduction to RNNs and sequence processing
Required Reading: Ch. 9
Optional Reading: TBA
10/02 Lecture 12
More on Neural Approaches to Sequence Modeling
Attention, Transformers and Contextual Embeddings
Required Reading: Ch. 10
Optional Reading: TBA
10/02–10/09 Quiz 4
10/07 Lecture 13
Machine Translation
Why is machinne translation difficult? A bit of history, some statistical ML
Required Reading: TBA
10/09 Lecture 14
More on Machine Translation
Statistical and Neural Models for MT
Required Reading: TBA
Optional Reading: TBA
10/09–10/16 Quiz 5
10/14 Lecture 15
Constituency Grammars and Parsing
Context-free grammars for English, CKY parsing
Required Reading: Ch. 12 and Ch. 13
Optional Reading: MS, Ch. 3, Woods (2010)
10/16 Lecture 16
Statistical Constituency Parsing
PCFGs, Treebank Parsing
Required Reading: Ch. 14
10/16–11/04 HW3
10/21 Lecture 17
Dependency Grammars and Parsing
Dependency Trees, Universal Dependencies, Shift-Reduce Parsing
Required Reading: Ch. 15
10/23 Lecture 18
Expressive Grammars
Going beyond CFGs (with a focus on categorial grammars)
Required Reading:
Optional Reading: Steedman & Baldridge (2011)
10/23–10/30 Quiz 6
10/28 Lecture 19
Compositional Semantics
What is the meaning of a sentence, and how can we represent it? Basic predicate logic and lambda calculus
Required Reading: Ch. 16
10/30 Lecture 20
Lexical Semantics
How do we represent the meaning of words?
Required Reading: Ch. 19
Optional Reading: TBA
10/30–11/06 Quiz 7
11/04 Lecture 21
Verb Semantics and Semantic Role Labeling
How do we represent and capture who does what to whom?
Required Reading: Ch. 20
11/06 Lecture 22
Referring Expressions and Coreference
How do we refer to entities in text? How do we identify the same mentions of the same entities?
Required Reading: Ch. 22
11/06–12/04 HW4
11/11 Lecture 23
Going beyond sentences: what makes longer texts coherent and cohesive?
Required Reading: Ch. 23
Optional Reading: TBA
11/13 Lecture 24
Information Extraction
Named Entity Recognition, Relation Extraction, Events
Required Reading: Ch. 18
Optional Reading: TBA
11/13–11/20 Quiz 8
11/18 Lecture 25
Question Answering
Retrieval vs. Knowledge-Based QA
Required Reading: Ch. 25
Optional Reading: TBA
11/20 Lecture 26
Properties of human conversation, chatbots vs. dialogue systems
Required Reading: Ch. 26
Optional Reading: TBA
11/20–12/04 Quiz 9
12/02 Lecture 27
Grounded NLP
How do we connect language to other modalities (e.g. vision, action)?
Required Reading: TBA
Optional Reading: TBA
12/04 Lecture 28
Ethics in NLP
Ethical considerations for NLP research and for real-world applications of NLP.
Required Reading: TBA
Optional Reading: ACL wiki on Ethics in NLP
12/04–12/11 Quiz 10
12/09 Lecture 29
Required Reading: TBA
Optional Reading: TBA