Closed e-caste closed 2 years ago
This is because the current model, https://huggingface.co/neuraly/bert-base-italian-cased-sentiment, uses the [, ] characters to define mask tokens. This means that everything between those characters is ignored by the model.
[
]
With square brackets (neutral at 81%):
Without square brackets (negative at 77%):
This issue stemmed from the suspicious results obtained by testing the Neuraly transformer (only 8% of accuracy against our currently labeled dataset) in commit https://github.com/WEEE-Open/skeeelled/commit/71fa6f98cdcd28aa060ce4352d071414d9c8adb1.
The issues are related to other characters' combination other than those associated to the masking. In commit 7c76f85 they have been removed from the inferred string but retained in the original comment. It is now functioning properly.
7c76f85
This is because the current model, https://huggingface.co/neuraly/bert-base-italian-cased-sentiment, uses the
[
,]
characters to define mask tokens. This means that everything between those characters is ignored by the model.With square brackets (neutral at 81%):
Without square brackets (negative at 77%):
This issue stemmed from the suspicious results obtained by testing the Neuraly transformer (only 8% of accuracy against our currently labeled dataset) in commit https://github.com/WEEE-Open/skeeelled/commit/71fa6f98cdcd28aa060ce4352d071414d9c8adb1.