Update README.md
Browse files
README.md
CHANGED
|
@@ -8,16 +8,28 @@ pinned: false
|
|
| 8 |
---
|
| 9 |
# Hyper Efficient System LLC
|
| 10 |
|
| 11 |
-
Research
|
| 12 |
-
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
### Bosnian Corpus v1.0 (cleaned)
|
| 17 |
-
- Zenodo
|
| 18 |
-
- Hugging Face Dataset:
|
| 19 |
|
| 20 |
### Entropy & Energy of the Bosnian Language
|
| 21 |
-
- Zenodo
|
| 22 |
-
- Hugging Face Dataset:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
# Hyper Efficient System LLC
|
| 10 |
|
| 11 |
+
Research and development company focused on applied AI, language technology,
|
| 12 |
+
information theory, and entropy-based modeling.
|
| 13 |
|
| 14 |
+
Our work spans large-scale language corpora, NLP infrastructure,
|
| 15 |
+
reproducible information-theoretic metrics (entropy, energy, redundancy),
|
| 16 |
+
and explainable, domain-specific AI systems for real-world applications.
|
| 17 |
+
|
| 18 |
+
## Featured projects
|
| 19 |
|
| 20 |
### Bosnian Corpus v1.0 (cleaned)
|
| 21 |
+
- Canonical release (Zenodo): 10.5281/zenodo.17757098
|
| 22 |
+
- Hugging Face Dataset: coming soon
|
| 23 |
|
| 24 |
### Entropy & Energy of the Bosnian Language
|
| 25 |
+
- Paper & assets (Zenodo): 10.5281/zenodo.17970788
|
| 26 |
+
- Hugging Face Dataset (metrics & assets): coming soon
|
| 27 |
+
|
| 28 |
+
## Research direction
|
| 29 |
+
|
| 30 |
+
While current public releases focus on Bosnian as a well-defined case study,
|
| 31 |
+
the underlying methodology is language-agnostic and designed for
|
| 32 |
+
multilingual and cross-linguistic analysis.
|
| 33 |
|
| 34 |
+
Additional language resources and comparative entropy-based benchmarks
|
| 35 |
+
are in active development.
|