# Probabilistic Typology: Deep Generative Models of Vowel Inventories

arXiv: https://arxiv.org/abs/1705.01684 · HTML: https://mlsanity.com/paper/1705.01684/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2017.

## Built on by (most cited first, 8 of 8)

- [Differentiable Subset Pruning of Transformer Heads](https://mlsanity.com/paper/2108.04657/) (2021)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Minimax and Neyman-Pearson Meta-Learning for Outlier Languages](https://mlsanity.com/paper/2106.01051/) (2021)
- [Diversity-Aware Batch Active Learning for Dependency Parsing](https://mlsanity.com/paper/2104.13936/) (2021)
- [Colexifications for Bootstrapping Cross-lingual Datasets: The Case of Phonology, Concreteness, and Affectiveness](https://mlsanity.com/paper/2306.02646/) (2023)
- [From `Snippet-lects' to Doculects and Dialects: Leveraging Neural Representations of Speech for Placing Audio Signals in a Language Landscape](https://mlsanity.com/paper/2305.18602/) (2023)
- [Tonguescape: Exploring Language Models Understanding of Vowel Articulation](https://mlsanity.com/paper/2501.17643/) (2025)
- [A General Divergence Modeling Strategy for Salient Object Detection](https://mlsanity.com/paper/2111.11827/) (2021)

## Abstract (arXiv)

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.