Papers by Hamed Waezi

Copied to clipboard

Challenge:	Existing models to detect predatory conversations for online conversation platforms are lacking in real-world applications due to sparse distribution of predatory conversation data.
Approach:	They propose backtranslation augmentation to augment training datasets with more predatory conversations by using 3 neural translators to augment them.
Outcome:	The proposed model improves with fewer training epochs for better classification efficacy on 8 languages from 4 language families and shows that it is more efficient than previous models.