Joint MTS-Skoltech Laboratory

 

The NLP group is privileged to lead a collaboration with the MTS AI in the field of Natural Language Processing (NLP) a subfield of Artificial Intelligence (AI). The joint laboratory features various projects focusing on developing cutting edge language processing technologies using modern statistical and neural approaches, as well as datasets to solve contemporary tasks on topics such as active learning for NLP, neural textual style transfer, and others.

This page contains a list of scientific publications resulting from this collaboration:

Journal articles

Conference proceedings

  • Shelmanov, A., Puzyrev, D., Kupriyanova, L., Belyakov, D., Larionov, D., Khromov, N., Kozlova, O., Artemova, E. Dylov, D. V., and Panchenko A. (2021): Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates. In Proceeding of the 16th conference of the European Chapter of the Association for Computational Linguistics (EACL). Kiev, Ukraine (online).
  • Shelmanov, A., Tsymbalov, E., Puzyrev, D., Fedyanin, K., Panchenko, A., Panov, M. (2021): How Certain is Your Transformer? In Proceeding of the 16th conference of the European Chapter of the Association for Computational Linguistics (EACL). Kiev, Ukraine (online). 

Workshop proceedings

Presentations

  • Nikolay Babakov, Daryna Dementieva, and Varvara Logacheva delivered three talks at the Trustworthy AI conference  respectively on fake news and propaganda detection, inappropriate message detection, and text detoxification.
  • An invited talk by Nikolay Babakov at the Crowd Science Seminar on detection of inappropriate messages. Video.

Press Releases