Metraipolis › archive › dc_aaddd10454fc

Universal or Language-Family-Specific Script Unification for Cross-Lingual Transfer? A Case Study on Turkic Languages — arXiv:2608.09356

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09356
License (as archived)
CC0-1.0
Archived
2026-10-19T08:50:21.325Z
SHA-256 of the archived text
85fbd0bebfcaea103fa980cf0734e108c242b2ca5a682a9f42b52c8ca7b86cb0
Stable URL of this page
https://metraipolis.com/documento/dc_aaddd10454fc

How to cite

Universal or Language-Family-Specific Script Unification for Cross-Lingual Transfer? A Case Study on Turkic Languages — arXiv:2608.09356 — arXiv (en), https://arxiv.org/abs/2608.09356 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aaddd10454fc (Metraipolis archive dc_aaddd10454fc, sha256 85fbd0bebfcaea103fa980cf0734e108c242b2ca5a682a9f42b52c8ca7b86cb0)
BibTeX
@misc{dcaaddd10454fc,
  title = {Universal or Language-Family-Specific Script Unification for Cross-Lingual Transfer? A Case Study on Turkic Languages — arXiv:2608.09356},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09356},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aaddd10454fc; sha256 85fbd0bebfcaea103fa980cf0734e108c242b2ca5a682a9f42b52c8ca7b86cb0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09356. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.09356 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T08:49:41.925Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).