Calibrating BERT-based Intent Classification Models: Part-2
Using temperature scaling and label smoothing to calibrate classification models
In Part-1 of this series, my colleague Ramji Chandrasekaran described the problem of unreliable confidence score outputs in BERT-based intent classifiers. In short, the problem was that confidence scores of an intent classification model were always saturating to a number close to 1, even when the predictions were incorrect.
Before Calibration (This Photo by Unknown Author is licensed under CC BY-SA and edited by…
As…