Universal or Language-Family-Specific Script Unification for Cross-Lingual Transfer? A Case Study on Turkic Languages
2026-08-10 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied how changing the writing system (script) of related Turkic languages helps computer language models understand them better. They compared a general method (uroman) and a language-family method (Common Turkic Script) to convert different scripts into a shared form. Both methods improved name recognition compared to original models, but results for part-of-speech tagging varied by language. The best approach depends on the language, how much the converted text overlaps at the character level, and if there is training data in the target language.
script unificationTurkic languagestransliterationfastTextnamed entity recognition (NER)part-of-speech tagging (POS)cross-lingual transferUniversal DependenciesWikiANNcharacter n-grams
Authors
Zijie Zhang
Abstract
Closely related languages written in different scripts expose little surface overlap to multilingual models, limiting cross-lingual transfer. We compare two approaches to script unification: the general-purpose uroman romanizer and the family-specific Common Turkic Script (CTS). We train matched fastText models on transliterated Wikipedia corpora from 11 Turkic languages and evaluate them on WikiANN named entity recognition and Universal Dependencies part-of-speech tagging. CTS and uroman show no significant difference on NER, while both substantially outperform the official monolingual fastText baselines. POS results reveal no universal winner: language-specific differences are associated with the cross-lingual character n-gram coverage induced by each representation, while within-language coverage becomes more important when target-language supervision is available. Although CANINE-c achieves higher overall POS averages, the substantially simpler fastText-based systems remain competitive on several treebanks. Overall, the effectiveness of script unification depends on the language, the induced subword overlap, and the available supervision.