Global access to the Internet has enabled the spread of information throughout the world and has offered many new possibilities. On the other hand, alongside the advantages, the exponential and uncontrolled growth of user-generated content on the Internet has also facilitated the spread of toxicity and hate speech. Much work has been done in the direction of offensive speech detection. However, there is another more proactive way to fight toxic speech -- how a suggestion for a user as a detoxified version of the message. In this presentation, we will provide an overview how texts detoxification task can be solved. The proposed approaches can be reused for any text style transfer task for both monolingual and multilingual use-cases.
Affiliation: Technical University of Munich
I am a postdoctoral researcher at TUM. Currenlty, I am involved into the project of eXplainable AI. In 2022, I obtained my PhD under the supervision of Pr. Alexander Panchenko, Skoltech. My PhD research was connected with such important sociological issues as Fake News Detection and Texts Detoxification. More broadly, I am super interested in the NLP for Social Good research direction. Besides academical experience, I also was involved in several industrial projects in different companies: Visiology, Moscow, Russian Federation; Beiersdorf, Hamburg, Germany. Now, obtained industrial experience helps me a lot in my research.