Difference between revisions of "Uyghur"

Revision as of 17:12, 6 February 2025

Uyghur is an official language of the Xinjiang Uyghur Autonomous Region spoken by the Uyghur people living in the region or neighboring countries including Kazakhstan, Kyrgyzstan, and Uzbekistan. There are around 8 to 11 million speaking according to 2021 estimates.

Resources

Computational

- Uyghur Keyboard:

• Uyghur Keyboard by Microsoft
• Uyghur Keyboard on Keyboard Layout

(These are copyrighted materials by Microsoft Corporation.)

- Uyghur Spell and Grammar Checker:

• Uyghur Spell Checker by LibreOffice
• Uyghur Grammar Checker by LingvaNex (This requires payment)

- Uyghur Alphabet and Scripts Converter:

• Latin to Uyghur Alphabet Converter by Temple University
• Uyghur-Multi-Script Converter by neouyghur

- Machine Translation Units:

• Information of Machine Translation APIs for Uyghur by Machine Translate.

The article mentioned 6 different machine translation APIs that supports Uyghur. However, a lot of these requires a subscription/payment for their services.

1. Microsoft Translator
2. LingvaNex
3. NeuralSpace
4. ModernMT
5. Baidu Translate (We could not find Uyghur on the site)
6. Google Translate

- The article also mentioned 2 different Quality Estimation APIs

1. TAUS Estimate APIs
2. ModelFront

All of these are either behind paywall, or requires further research on it to ensure that the translation is offered.

Dictionaries and Glossaries

• Concise Dictionary of Modern Uyghur Grammar
• An Uyghur-English Dictionary by Henry G. Schwarz, Western Washington University
• Uyghur Dictionary by Lexigos

Grammatical Descriptions

• Uyghur language grammatical lessons for kids
• Greetings from the Teklimakan: a handbook of Modern Uyghur (volume 1)

Scientific Works

- These are the scientific papers on some of the features on Uyghur:

• A Review of Morphological Analysis Methods on Uyghur Language
• Morphological disambiguation rules for Uyghur language
• Rule-Based Analysis of the Uyghur Nouns

- This research delved into some aspect of Uyghur's loan words: An Analysis of recent loans into the standard Uyghur Lexicon

- This dissertation by Dr. Connor Mayer could contain useful information: Issues in Uyghur backness harmony: Corpus, experimental, and computational studies

- Miscellaneous research related to Uyghur that may (or may not) prove to be useful:

• Noisy Uyghur Text Normalization
• Computational Comparison of the Uyghur and Turkish Grammar

- Some research on building Uyghur WordNet Dataset:

• Building Contemporary Uyghur Grammatical Information Dictionary
• Construction of an English-Uyghur WordNet Dataset

- This is not related per se, but it is an interesting research. Some useful information could be extracted:

• Eye movements guided by morphological structure: Evidence from the Uighur language

Corpora

• Uygur.com, a website containing digital scans of books and texts written in Uyghur. Most of these are photocopied and might be hard to parse into a text file
• Genesis 1, a translation of Genesis into Uyghur
• Radio Free Asia, a news website with articles in Uyghur
• Quran, a pdf of the Quran in Uyghur, also photocopied so it may be hard to parse