Ryan Cotterell will give a talk on Monday, November 12, at 4pm in the IACS seminar room. The talk is co-hosted as part of the Frontiers Talk series in the Department of the Linguistics and the NLP group of the Department of Computer Science.
Ryan is the winner of the ACL 2017 best paper award. He is currently finishing his PhD at Johns Hopkins University and about to start a position at Cambridge University.
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.