Title: Probabilistic Typology: Deep Generative Models of Vowel Inventories

Abstract: Linguistic typology studies the range of structures present in human language. The main goal of the field is to discover which sets of possible phenomena are universal, and which are merely frequent. For example, all languages have vowels, while most—but not all—languages have an [u] sound. In this paper we present the first probabilistic treatment of a basic question in phonological typology: What makes a natural vowel inventory? We introduce a series of deep stochastic point processes, and contrast them with previous computational, simulation-based approaches. We provide a comprehensive suite of experiments on over 200 distinct languages.

Bio: I am a fourth year Ph.D. student in the Johns Hopkins Computer Science department affiliated with the Center for Language and Speech Processing, where I am co-advised by Jason Eisner and David Yarowsky. I specialize in Natural Language Processing, Computational Linguistics and Machine Learning, focusing on deep learning and statistical approaches to phonology, morphology, linguistic typology and low-resource languages.

This talk is co-coordinated by CBMM and CompLang.

CompLang is a student-run discussion group on language and computation that takes place at MIT. The aim of the group is to bring together the language community at MIT and nearby, learn about each other's research, and foster cross-laboratory collaborations.