Description NB: this version of the model is the improved version of EIStakovskii/french toxicity classifier plus. To see the source code of training and the data please follow the github link. This model was trained for toxicity labeling. The model was fine tuned based off the CamemBERT language model. To use the model: Metrics (at validation): epoch step eval accuracy eval f1 eval loss 1.16 1600 0.9015412511332729 0.8968269048071442 0.3014959990978241 Comparison against Perspective This model was compared against the Google's Perspective API that similarly detects toxicity. Two models were tested on two datasets: the size of 200 sentences and 400 sentences. The first one (arguably harder) was collected from the sentences of the JigSaw and DeTox datasets. The second one (easier) was collected from the combination of sources: both from JigSaw and DeTox as well as Paradetox translations and sentences extracted from Reverso Context by keywords. french toxicity classifier plus v2 size accuracy f1 200 0.783 0.803 400 0.890 0.879 Perspective size accuracy f1 200 0.826 0.795 400 0.632 0.418 I suspect that Perspective has such a low score in the case of the FR dataset (400) because it ref…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy