Computational linguistics develops mathematically precise computational models of language learning, use, and understanding, which are deployed in one of two ways. First, they can be used scientifically to understand the consequences of the complex assumptions that are often made in theories of language learning or use. By formalizing hypotheses, we can deduce outcomes that would be difficult or impossible to understand without simulation and/or proof, and we can often derive new kinds of predictions from our theories. Second, such implemented computational models are important as engineering tools in real-world applications, such as interaction with our phones and computers.
At McGill, research in computational linguistics is strong in scientific applications in the Linguistics department, and in engineering applications in the university more broadly. In the department we use a variety of computational tools and methods to study language acquisition, processing, use in society, and change over time. One focus is structured probabilistic models of phonology, morphology, and syntax which make use of linguistic theories in these domains and methods from machine learning and artificial intellience. Another focus is adapting methods from computer science to develop tools for analyzing large speech datasets.
Computational Models of Language Learning and Processing
Siva ReddyEffective Start Date: January 2020
Linguistically-Informed Deep Learning
Computational Syntax and Semantics
Biases in Deep Learning Models
Researchers from Other Departments
We also have connections with computational researchers in other departments at McGill:
- Jackie Cheung (Computer Science) uses statistical methods from artificial intelligence and machine learning to generate text and speech that is fluent and appropriate to context.
- Derek Ruths (Computer Science) analyzes large-scale human behavior on Twitter and other online forums.
- McGill's Digital Humanities community, led by Andrew Piper and Stéfan Sinclair (Languages, Literatures, and Cultures), analyze textual data using computational methods to address questions about literature, culture, and society.