Method
A frozen multilingual MiniLM encoder and trained MLP classifier, compared with TF-IDF.
Request text→Category and model score
APPLIED INTELLIGENCE / Text classification

Recorded local application view. This image is not an interactive interface.
RESULT AND CONTEXT
A frozen multilingual MiniLM encoder and trained MLP classifier, compared with TF-IDF.
Accuracy on 12 authored Polish examples: 66.67%. This is not a representative Polish benchmark.
Results come from the project reports. This presentation does not include retraining or independent evaluation.
YOUR NEXT PROJECT