arXiv:1705.01684
Probabilistic Typology: Deep Generative Models of Vowel Inventories
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval
Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection
Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project
Evaluating Uncertainty in Deep Gaussian Processes
Whenever, Wherever: Towards Orchestrating Crowd Simulations with Spatio-Temporal Spawn Dynamics
Differentiable Adversarial Attacks for Marked Temporal Point Processes
토론
이 논문과 연결된 포럼 글이 아직 없습니다.