# Learning to pronounce as measuring cross-lingual joint orthography-phonology complexity

arXiv: https://arxiv.org/abs/2202.00794 · HTML: https://mlsanity.com/paper/2202.00794/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 11 references that are in the map.
- First posted on arXiv 29 Jan 2022.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Information-Theoretic Probing for Linguistic Structure](https://mlsanity.com/paper/2004.03061/) (2020)
- [Applying the Transformer to Character-level Transduction](https://mlsanity.com/paper/2005.10213/) (2020)
- [Transformer based Grapheme-to-Phoneme Conversion](https://mlsanity.com/paper/2004.06338/) (2020)
- [OTEANN: Estimating the Transparency of Orthographies with an Artificial Neural Network](https://mlsanity.com/paper/1912.13321/) (2019)

## Abstract (arXiv)

Machine learning models allow us to compare languages by showing how hard a task in each language might be to learn and perform well on. Following this line of investigation, we explore what makes a language "hard to pronounce" by modelling the task of grapheme-to-phoneme (g2p) transliteration. By training a character-level transformer model on this task across 22 languages and measuring the model's proficiency against its grapheme and phoneme inventories, we show that certain characteristics emerge that separate easier and harder languages with respect to learning to pronounce. Namely the complexity of a language's pronunciation from its orthography is due to the expressive or simplicity of its grapheme-to-phoneme mapping. Further discussion illustrates how future studies should consider relative data sparsity per language to design fairer cross-lingual comparison tasks.