EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semantic CodeSwitching for LowResource Language Adaptation

Santosh Srinath Kaza, Abhijit Das

Transactions of the Association for Computational Linguistics · 13.10.2026 · 14 · 2688-2707

DOI: 10.1162/tacl.a.821 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 13.10.2026. Verfasst von Santosh Srinath Kaza und 1 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-lingual adaptation remains a significant challenge for Large Language Models (LLMs) and Vision-Language Models (VLMs), particularly for low-resource languages. While the synthetic generation of code-switched text is an effective cross-lingual adaptation strategy, stochastic word replacement often degrades semantic integrity. We propose Semantic Code-Switching (SCS), a framework ensuring high-fidelity cross-lingual augmentation. We first train a Semantic Alignment Scorer to predict contextual similarity between matrix and code-switched sentences, then integrate this scorer into training pipelines via temperature-scaled sampling. Across diverse tasks, SCS consistently outperforms baselines like CoSDA-ML. Our method is especially robust for typologically distant languages, offering a scalable solution for multilingual adaptation without requiring parallel corpora.

Zitieren

APA

Kaza, S. S., & Das, A. (2026). Semantic CodeSwitching for LowResource Language Adaptation. Transactions of the Association for Computational Linguistics, 14, 2688-2707. https://doi.org/10.1162/tacl.a.821

Vancouver

Kaza SS, Das A. Semantic CodeSwitching for LowResource Language Adaptation. Transactions of the Association for Computational Linguistics. 2026;14:2688-2707. doi:10.1162/tacl.a.821

BibTeX
@article{Kaza2026,
  author = {Kaza, Santosh Srinath and Das, Abhijit},
  title = {Semantic CodeSwitching for LowResource Language Adaptation},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2026},
  volume = {14},
  pages = {2688--2707},
  doi = {10.1162/tacl.a.821}
}
Kostenlos starten →