# Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

arXiv: https://arxiv.org/abs/2010.11054 · HTML: https://mlsanity.com/paper/2010.11054/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [Ancient Script Image Recognition and Processing: A Review](https://mlsanity.com/paper/2506.19208/) (2025)
- [DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning](https://mlsanity.com/paper/2306.01268/) (2023)
- [Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI](https://mlsanity.com/paper/2310.09091/) (2023)
- [DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms](https://mlsanity.com/paper/2503.03644/) (2025)
- [Mergen: The First Manchu-Korean Machine Translation Model Trained on Augmented Data](https://mlsanity.com/paper/2311.17492/) (2023)
- [Decipherment-Aware Multilingual Learning in Jointly Trained Language Models](https://mlsanity.com/paper/2406.07231/) (2024)
- [Curation of a Palaeohispanic Dataset for Machine Learning](https://mlsanity.com/paper/2604.13070/) (2026)
- [We Hebben Een Serieus Translatie: Modeling Intercomprehension as Probabilistic Inference](https://mlsanity.com/paper/2607.12169/) (2026)
- [Tangut Word Segmentation under Extreme Resource Scarcity: Integrating Traditional Lexicons and Unlabeled Text](https://mlsanity.com/paper/2608.18437/) (2026)

## Abstract (arXiv)

Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest known language is not determined. We propose a decipherment model that handles both of these challenges by building on rich linguistic constraints reflecting consistent patterns in historical sound change. We capture the natural phonological geometry by learning character embeddings based on the International Phonetic Alphabet (IPA). The resulting generative framework jointly models word segmentation and cognate alignment, informed by phonological constraints. We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian). The experiments show that incorporating phonetic geometry leads to clear and consistent gains. Additionally, we propose a measure for language closeness which correctly identifies related languages for Gothic and Ugaritic. For Iberian, the method does not show strong evidence supporting Basque as a related language, concurring with the favored position by the current scholarship.