Picture for Olga Kozlova

Olga Kozlova

Text Detoxification using Large Pre-trained Neural Models

Sep 18, 2021
David Dale, Anton Voronov, Daryna Dementieva, Varvara Logacheva, Olga Kozlova, Nikita Semenov, Alexander Panchenko

Figure 1 for Text Detoxification using Large Pre-trained Neural Models

Figure 2 for Text Detoxification using Large Pre-trained Neural Models

Figure 3 for Text Detoxification using Large Pre-trained Neural Models

Figure 4 for Text Detoxification using Large Pre-trained Neural Models

* Submitted to the EMNLP 2021 conference

Access Paper or Ask Questions

Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation

Mar 09, 2021
Nikolay Babakov, Varvara Logacheva, Olga Kozlova, Nikita Semenov, Alexander Panchenko

Figure 1 for Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation

Figure 2 for Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation

Figure 3 for Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation

Figure 4 for Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation

* Accepted to the Balto-Slavic NLP workshop 2021 co-located with EACL-2021

Access Paper or Ask Questions

Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates

Feb 18, 2021
Artem Shelmanov, Dmitri Puzyrev, Lyubov Kupriyanova, Denis Belyakov, Daniil Larionov, Nikita Khromov, Olga Kozlova, Ekaterina Artemova, Dmitry V. Dylov, Alexander Panchenko

Figure 1 for Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates

Figure 2 for Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates

Figure 3 for Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates

Figure 4 for Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates

* In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2021)

Access Paper or Ask Questions