EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hierarchical Curriculum Transfer for Swahili QA with mT5: SQuAD Pretraining and KenSwQuAD Extractive-to-Abstractive Refinement

Jared Ongaro, Benjamin Kikwai

International Journal of Mathematics, Statistics, and Computer Science · 2026

DOI: 10.59543/14d9kq02 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Mathematics, Statistics, and Computer Science, 2026. Verfasst von Jared Ongaro und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The introduction of the Kencorpus Swahili Question Answering Dataset (KenSwQuAD) presents a compelling opportunity to advance Machine Reading Comprehension (MRC) for the Swahili language. However, the mixed composition of this dataset—comprising 67.6\% extractive and 32.4\% abstractive answers—introduces substantial hurdles for standard training pipelines. In this study, we benchmark the performance of the multilingual T5 (mT5) architecture on KenSwQuAD, deploying a robust Hierarchical Curriculum Learning strategy. We introduce a novel data restructuring technique that algorithmically partitions the corpus into distinct extractive and abstractive subsets, thereby enabling meticulously phased fine-tuning. By sequentially progressing from structural transfer via the English SQuAD, to morphological alignment on the Swahili extractive subset, and culminating in abstractive refinement, we establish that the mT5-base model can achieve a SacreBLEU score of 48.99 on extractive tasks. For abstractive reasoning, whilst the BLEU score is comparatively modest (15.52), the model attains a remarkable BERTScore F1 of 77.21\%, reflecting a profound degree of semantic comprehension. Furthermore, we evaluate the utility of structure-aware input formatting (context scaffolding) for successfully navigating extensive narrative contexts. Ultimately, our findings indicate that whilst modern transformer architectures can successfully internalise Swahili QA logic, a persistent fluency gap characterises the abstractive domain. This gap underscores the urgent necessity for more expansive, targeted datasets to reconcile semantic accuracy with lexical precision.

Zitieren

APA

Ongaro, J., & Kikwai, B. (2026). Hierarchical Curriculum Transfer for Swahili QA with mT5: SQuAD Pretraining and KenSwQuAD Extractive-to-Abstractive Refinement. International Journal of Mathematics, Statistics, and Computer Science. https://doi.org/10.59543/14d9kq02

Vancouver

Ongaro J, Kikwai B. Hierarchical Curriculum Transfer for Swahili QA with mT5: SQuAD Pretraining and KenSwQuAD Extractive-to-Abstractive Refinement. International Journal of Mathematics, Statistics, and Computer Science. 2026. doi:10.59543/14d9kq02

BibTeX
@article{Ongaro2026,
  author = {Ongaro, Jared and Kikwai, Benjamin},
  title = {Hierarchical Curriculum Transfer for Swahili QA with mT5: SQuAD Pretraining and KenSwQuAD Extractive-to-Abstractive Refinement},
  journal = {International Journal of Mathematics, Statistics, and Computer Science},
  year = {2026},
  doi = {10.59543/14d9kq02}
}
Kostenlos starten →