This is the cointegrated/rubert tiny model fine tuned for classification of toxicity and inappropriateness for short informal Russian texts, such as comments in social networks. The problem is formulated as multilabel classification with the following classes: non toxic : the text does NOT contain insults, obscenities, and threats, in the sense of the OK ML Cup competition. insult obscenity threat dangerous : the text is inappropriate, in the sense of Babakov et.al., i.e. it can harm the reputation of the speaker. A text can be considered safe if it is BOTH non toxic and NOT dangerous . Usage The function below estimates the probability that the text is either toxic OR dangerous: Training The model has been trained on the joint dataset of OK ML Cup and Babakov et.al. with Adam optimizer, the learning rate of 1e 5 , and batch size of 64 for 15 epochs in this Colab notebook. A text was considered inappropriate if its inappropriateness score was higher than 0.8, and appropriate if it was lower than 0.2. The per label ROC AUC on the dev set is:
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy