EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

ChavacanoMNMT: Exploring Language Influences in the Multilingual Neural Machine Translation of a Spanish-Based Creole

Aileen Joan Vicente, Charibeth Cheng

ACM Transactions on Asian and Low-Resource Language Information Processing · 30.11.2026 · 25 (11) · 1-18

DOI: 10.1145/3860330 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 05.11.2026. Verfasst von Aileen Joan Vicente und 1 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multilingual Neural Machine Translation (MNMT) enhances low-resource language translation by leveraging related languages, yet its application to Creole languages like Chavacano, a Spanish-based Creole spoken in the Philippines, remains underexplored. This study investigates the influence of Austronesian (Cebuano, Hiligaynon) and Indo-European (Spanish, English) parent languages on Chavacano MNMT performance. We fine-tuned an mT5-base model on the ChavacanoMT dataset, which comprises 1,044,185 samples spanning 20 language pairs involving Chavacano and related languages. Ablation experiments were conducted by excluding individual languages from training to evaluate their impact on model performance. Performance was assessed using BLEU, chrF++, and BERTScore metrics, with Paired Bootstrap Resampling applied to determine statistical significance. This study reports that Austronesian languages significantly influence Chavacano translation quality more than Indo-European languages (5 BLEU points, p =0.001). Cebuano and Hiligaynon enhance translation quality ( p ⪋0.025), while Spanish contributes less due to structural divergence (VSO vs. SVO) despite Chavacano’s 77% lexical similarity with Spanish. Our model achieves a 17 BLEU point improvement in Chavacano-English translation over prior benchmarks. These findings highlight the role of structural similarity in MNMT and inform auxiliary language selection for low-resource Creole translation, contributing new benchmarks and insights for Chavacano NLP.

Zitieren

APA

Vicente, A. J., & Cheng, C. (2026). ChavacanoMNMT: Exploring Language Influences in the Multilingual Neural Machine Translation of a Spanish-Based Creole. ACM Transactions on Asian and Low-Resource Language Information Processing, 25(11), 1-18. https://doi.org/10.1145/3860330

Vancouver

Vicente AJ, Cheng C. ChavacanoMNMT: Exploring Language Influences in the Multilingual Neural Machine Translation of a Spanish-Based Creole. ACM Transactions on Asian and Low-Resource Language Information Processing. 2026;25(11):1-18. doi:10.1145/3860330

BibTeX
@article{Vicente2026,
  author = {Vicente, Aileen Joan and Cheng, Charibeth},
  title = {ChavacanoMNMT: Exploring Language Influences in the Multilingual Neural Machine Translation of a Spanish-Based Creole},
  journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
  year = {2026},
  volume = {25},
  number = {11},
  pages = {1--18},
  doi = {10.1145/3860330}
}
Kostenlos starten →