Exploring Deep Latent Variables in NLP

Yoon Kim is currently a Research Scientist at the MIT-IBM AI Watson Lab, and will be joining MIT as an assistant professor in 2021. Yoon’s research focuses on machine learning and natural language processing. His PhD thesis is titled "Deep Latent Variable Models of Natural Language", which he completed in 2020 at Harvard University. We discuss his work on uncovering latent structure in natural language, including continuous vector representations, tree structures, and grammars. We cover learning and variational inference methods that he developed during his PhD, and he offers a look at where latent variable models will be heading in the future. Episode notes: https://cs.nyu.edu/~welleck/episode6.html Follow the Thesis Review (@thesisreview) and Sean Welleck (@wellecks) on Twitter, and find out more info about the show at https://cs.nyu.edu/~welleck/podcast.html Support The Thesis Review at www.buymeacoffee.com/thesisreview