LIN350 Computational semantics: Schedule
This schedule is subject to change.
Assignments are due at class time (12pm) on their due date. Please submit assignments online on Canvas unless the assignment tells you otherwise.
Readings can be done either before or after class (unless noted otherwise); they are chosen to support the material covered in class.
Jan 27. Programming: Functions in Python. Then starting on conditions and lists
Jan 29. Programming: Conditions, lists, and loops
Jan 31. Programming: Dictionaries
Feb 3 Count-based embeddings: an overview
See the slides on Canvas (distmodels_countbased)
An accessible introduction to count-based models is in Section 2 of this paper (but only that section)
Feb 5 Count-based embeddings in detail
Feb 7 What can I do for my project?
Feb 17 Logistic regression, word2vec, and neural models: Step 2: Logistic regression
Readings: Jurafsky and Martin ed. 3, chapter 5
This goes into much more detail than we did in class. You don't need to read up on details that we did not cover, but you can if you are curious.
Feb 19 Logistic regression, word2vec, and neural models: Step 3: word2vec
This goes into more detail than we did in class. You don't need to read up on details that we did not cover, but you can if you are curious.
Feb 21 Prediction-based embeddings in practice:
How to compute them, and how to test whether they are okay
We revisit the demo: using a pre-trained space in gensim
Feb 24 We talk in class about your project ideas.
Feb 26 Testing embeddings: correlation with human judgments.
Rubenstein and Goodenough: on Canvas
The original version is also on Canvas.
Feb 28 Using embeddings: vector arithmetic
Mar 2 Using embeddings: word sense induction
Mar 4 Using embeddings: lexical inference; embeddings and classifiers
Homework 2 due.
Mar 6 Topic modeling: automatically detecting underlying themes in documents
Mar 9 Topic modeling, continued
Mar 11 Logistic regression, word2vec, and neural models: Step 4: deep neural networks
Initial project description due.
Mar 13 Class canceled due to COVID
Classes canceled due to COVID
Mar 30 An introduction to logic
April 1 Propositional logic and first-order logic
April 3 Propositional logic and first-order logic
April 6 Language and logic:
"There is in my opinion no important theoretical difference between natural languages and the artificial languages of logicians." (Richard Montague)
April 8 Language, logic, and inference
April 10 Semantics construction: automatically constructing a logical representation for a sentence
Homework 3 due.
April 13 Semantics construction and lambda calculus: lego for logic
April 15: more semantics construction
Examples of lambda calculus: see Canvas, file lambda_examples.pdf
April 17 Finishing up semantics construction. Then:
Logic-based semantics in the Natural Language Toolkit
Intermediate project report due.
April 20: Practicing semantics construction
April 22: Practicing semantics construction
April 24: Automatic theorem proving: automatically drawing inferences from collections of logical formulas
Also: Scaled-up semantics construction: the Groningen MeaningBank
April 27 Contextualized embeddings
April 29 Outlook: integrating logic and embeddings
Homework 4 due.
May 1 Outlook: integrating logic and embeddings
May 4: Project presentations:
2:00: Rohan Nair and Lindia Tjuatja
2:08: Blake Davis
2:16: Tabitha Kaiser and Kylie Heitzenrater
2:24: Austin Leonard and Yucong Yang
2:32: David Alvarez and Abbie Amick
May 6: Project presentations:
2:00 Daniel Escobar and Xavier Jan Concepcion
2:08: Zach Holsinger
2:16: Sommer Chavez and Miguel Arriaga
2:24: Isaiah Hogue
2:32: Pepper Dawes and Jasmin Thairintr
May 8: Project presentations:
2:00 Vincent Lee
2:08 Michael Sullivan
2:16: Anurag Singh and Alexander Houy
2:24 Ed Pedraza-Robles and Ryan Schulze
2:32: Rebecca Harrison and Gabrielle Shaddock
... and some final words.
Final report due: Thursday May 14, 12pm.