Digitizing Humanities in South Africa: Computational linguistic resources, training, and community building
Bibliographic record
Abstract
South Africa has eleven official languages. However, not all have received similar amounts of attention. In particular, for many of the languages, only a limited number of digital language resources (data sets and computational tools) exist. This scarcity hinders (computational) research in the fields of humanities and social sciences for these languages. Additionally, using existing computational linguistics tools in a practical setting requires expert knowledge on the usage of these tools. In South Africa, only a small number of people currently have this expertise, further limiting the type of research that relies on computational linguistic tools. The South African Centre for Digital Language Resources (SADiLaR) aims to enable and enhance research in the area of language technology by focusing on the development, management, and distribution of digital language resources for all South African languages. Additionally, it aims to build research capacity, specifically in the field of digital humanities. This requires several challenges to be resolved that we cluster under resources, training, and community building. SADiLaR hosts a repository of existing digital language resources and supports the development of new resources. Additionally, it provides training on the use of these resources, specifically for (but not limited to) researchers in the fields of humanities and social sciences. Through this training, SADiLaR tries to build a community of practice to boost information sharing in the area of digital humanities.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.037 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.010 | 0.012 |
| Science and technology studies | 0.006 | 0.004 |
| Scholarly communication | 0.007 | 0.017 |
| Open science | 0.003 | 0.017 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.026 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".