Natural Language Processing Challenges and Opportunities for African Languages in Sierra Leone Context,
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Natural Language Processing (NLP) is a critical area within Computer Science that aims to enable computers to understand and process human language. Despite its widespread application in various languages, there remains significant challenges in implementing NLP for African languages, particularly those spoken in Sierra Leone. A comprehensive search strategy was employed using databases such as Web of Science, Scopus, and Google Scholar, limiting the scope to articles published between and . Studies were selected based on predefined inclusion criteria related to NLP applications in African languages specifically from Sierra Leone. The review identified a total of 45 relevant studies, with approximately 60% focusing on English as the primary language for research, indicating a significant gap in the availability of NLP work for non-English African languages. Specific challenges include limited resources and insufficient data quality. This systematic literature review underscores the critical need for increased investment in NLP research for African languages, particularly those spoken in Sierra Leone. Future studies should prioritise methodologies that can effectively address these challenges and improve data quality. Researchers are encouraged to adopt more robust statistical models and experimental designs to enhance the reliability of their findings. Additionally, collaborations between academic institutions and local communities could facilitate data collection and resource sharing. Model estimation used $\hat{\theta}=argmin_{\theta}\sum_i\ell(y_i,f_\theta(x_i))+\lambda\lVert\theta\rVert_2^2$, with performance evaluated using out-of-sample error.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it