EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Representational Adequacy in Bantu Language Resources: Tone as a Case for Relational Language Databases

Mpho Primus, Sabine Zerbian

Journal of the Digital Humanities Association of Southern Africa (DHASA) · 20.11.2026 · 7 (2) · 36-45

DOI: 10.55492/dhasa.v7i02.7687 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Digital Humanities Association of Southern Africa (DHASA), online erschienen am 20.11.2026. Verfasst von Mpho Primus und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Language models typically treat orthographic text as sufficient, but for Bantu languages like Sesotho, this text omits linguistic features such as tone and vowel quality, leading to ambiguities. We argue this is a representational, not data, problem. We propose shifting from static corpora to property-graph, multimodal, versioned databases that link orthography with speech, phonology, morphology, syntax, semantics, variation, and provenance, enabling task-specific dataset generation. Developing such databases requires linguistic expertise; we outline a curriculum to build capacity for creating phonological and phonetic representations, including tone, for computational use.

Zitieren

APA

Primus, M., & Zerbian, S. (2026). Representational Adequacy in Bantu Language Resources: Tone as a Case for Relational Language Databases. Journal of the Digital Humanities Association of Southern Africa (DHASA), 7(2), 36-45. https://doi.org/10.55492/dhasa.v7i02.7687

Vancouver

Primus M, Zerbian S. Representational Adequacy in Bantu Language Resources: Tone as a Case for Relational Language Databases. Journal of the Digital Humanities Association of Southern Africa (DHASA). 2026;7(2):36-45. doi:10.55492/dhasa.v7i02.7687

BibTeX
@article{Primus2026,
  author = {Primus, Mpho and Zerbian, Sabine},
  title = {Representational Adequacy in Bantu Language Resources: Tone as a Case for Relational Language Databases},
  journal = {Journal of the Digital Humanities Association of Southern Africa (DHASA)},
  year = {2026},
  volume = {7},
  number = {2},
  pages = {36--45},
  doi = {10.55492/dhasa.v7i02.7687}
}
Kostenlos starten →