neuraly/bert-base-italian-cased-sentiment

The neuraly - Italian BERT Sentiment model performs sentiment analysis on Italian sentences . It was trained starting from an instance of bert-base-italian-cased, and fine-tuned on an Italian dataset of tweets, reaching 82% of accuracy on the latter one . The model was trained with a Log Likelyhood + Softmax combined loss, hence to extract probabilities we need a softmax on top of the logits tensor . The domain is strongly related to football players and teams, but it works surprisingly well even on other topics . It is possible to download the model from their S3 storage and live test it from their inference API . It achieves an overall accuracy on,