Teaching
Current Courses
Intro to Computational Linguistics
Covers foundational concepts in computational linguistics for students with strong linguistic backgrounds. Emphasizes formal languages as analytical tools and teaches algorithm implementation, including finite state phonological and morphological parsing, and syntactic parsing.
Statistical Methods in Linguistics
Introduction to probability and statistics for linguistics. Topics include elementary probability theory, descriptive and inferential statistics, machine learning concepts, and fixed and mixed effects models. Concepts explored through linguistic case studies including judgment data, reaction times, and acoustic measurements.
Previously Taught
Statistical Methods in Computational Linguistics
Focuses on deployment of statistical methods for advancing linguistic theory and designing statistical models. Topics include phonetic category perception and learning, phonotactic, morphological, and syntactic grammar induction.
Deep Learning Methods in Computational Linguistics
Advanced topics emphasizing deployment of deep learning methods for advancing linguistic theory. Covers phonotactic, morphological, and syntactic grammar induction as well as morphological, syntactic and semantic parsing.
Intro to Semantic Analysis
Introduces analyzing meaning in natural language through formal/logical methods. Employs logical notation to analyze natural language meaning using truth-conditions, set theory, and the relationship between meaning and syntactic/lexical structure.
Computational Semantics
Hands-on course covering two areas: implementing traditional rule-based compositional semantics in Haskell, and exploring distributional semantic models where meaning derives from lexical co-occurrence in large-scale corpus resources.
Natural Language Processing
Introduces NLP with focus on programs that comprehend natural language. Covers English syntax, parsing techniques, semantic analysis, speech acts, knowledge representation, and NLP system design.