# Clarifying orthography: Orthographic transparency as compressibility

arXiv: https://arxiv.org/abs/2505.13657 · HTML: https://mlsanity.com/paper/2505.13657/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 28 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 2 of 2)

- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [The Description Length of Deep Learning Models](https://mlsanity.com/paper/1802.07044/) (2018)

## Built on by (most cited first, 1 of 1)

- [Removable and Irreducible: A Token-Cost Ledger for the Multilingual Tokenization Tax](https://mlsanity.com/paper/2609.00378/) (2026)

## Abstract (arXiv)

Orthographic transparency -- how directly spelling is related to sound -- lacks a unified, script-agnostic metric. Using ideas from algorithmic information theory, we quantify orthographic transparency in terms of the mutual compressibility between orthographic and phonological strings. Our measure provides a principled way to combine two factors that decrease orthographic transparency, capturing both irregular spellings and rule complexity in one quantity. We estimate our transparency measure using prequential code-lengths derived from neural sequence models. Evaluating 22 languages across a broad range of script types (alphabetic, abjad, abugida, syllabic, logographic) confirms common intuitions about relative transparency of scripts. Mutual compressibility offers a simple, principled, and general yardstick for orthographic transparency.