Course Webpages, tutorials, slide decks, and other materials that might be useful to people getting into computational linguistics, psycholinguistics, or something similar.

Courses

Below are links to the most recent websites for courses that I’ve taught at Macalester, with the majority of resources available to the public!

Algorithmic Design & Analysis — SP25 Theory of Computation — SP25 Natural Language Processing – FA24

Tutorials

Neural Networks & Language Processing (Slides, Notebook 1, and Notebook 2). Materials from an LSA 2022 minicourse co-taught by me and Brian Dillon.

Training LSTM Language Models for Psycholinguistics (WIP). A walkthrough (with commentary) of the code used by Gulordava et al. (2018) to train LSTM language models with a focus on psycholinguistic evaluation.

Psycholinguistic Evaluation of Language Models. A tutorial designed for a Computational Psycholinguistics class at JHU CogSci (2018) to introduce the techniques necessary for psycholinguistic evaluation of neural language models.

Slide Decks

Note that slide decks were designed to be used as a visual aid within a presentation and have (mostly) not been modified, so they are not entirely self contained. They are probably best used as a companion to another more comprehensive, bit perhaps more dense, resource. In that case, reconstructing the presentation of each slide is left as an exercise to the reader :)

Memory and Language Processing. Slide deck from a guest lecture in JHU CogSci’s Computational Psycholinguistics class (2019) on the relationship between models of memory and language processing (ACT-R, Interference Effects, etc.).

Introduction to Language Processing. Slide deck from a guest lecture in JHU CogSci’s Language and Mind class introducing students to the core methods and ideas in psycholinguistics (Competence/Performance, Lexical Priming, Automaticity, Incremental Parsing, etc.).

Variational Inference in ML. Slide deck from a presentation in the JHU CAP Lab Lab Meeting (June 2019) motivating and introducing Variational Inference as a tool for unsupervised learning.