# Uzbek Cyrillic-Latin-Cyrillic Machine Transliteration

arXiv: https://arxiv.org/abs/2101.05162 · HTML: https://mlsanity.com/paper/2101.05162/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 8 references that are in the map.
- First posted on arXiv 13 Jan 2021.

## Builds on (most cited first, 1 of 1)

- [Sequence to Sequence Networks for Roman-Urdu to Urdu Transliteration](https://mlsanity.com/paper/1712.02959/) (2017)

## Built on by (most cited first, 4 of 4)

- [SimRelUz: Similarity and Relatedness scores as a Semantic Evaluation dataset for Uzbek language](https://mlsanity.com/paper/2205.06072/) (2022)
- [A machine transliteration tool between Uzbek alphabets](https://mlsanity.com/paper/2205.09578/) (2022)
- [UzBERT: pretraining a BERT model for Uzbek](https://mlsanity.com/paper/2108.09814/) (2021)
- [Towards Transliteration between Sindhi Scripts from Devanagari to Perso-Arabic](https://mlsanity.com/paper/2305.07365/) (2023)

## Abstract (arXiv)

In this paper, we introduce a data-driven approach to transliterating Uzbek dictionary words from the Cyrillic script into the Latin script, and vice versa. We heuristically align characters of words in the source script with sub-strings of the corresponding words in the target script and train a decision tree classifier that learns these alignments. On the test set, our Cyrillic to Latin model achieves a character level micro-averaged F1 score of 0.9992, and our Latin to Cyrillic model achieves the score of 0.9959. Our contribution is a novel method of producing machine transliterated texts for the low-resource Uzbek language.