Scholar
Nikolay Babakov
Google Scholar ID: y9Ju0gcAAAAJ
University of Santiago de Compostela
Citations & Impact
Citations
244
H-index
10
i10-index
10
Publications
20
Co-authors
41
list available
Publications
Resume (English only)
Academic Achievements
- Papers: Available on Google Scholar.
- Blog: ButterflAI effect, a blog where he collects interesting examples of AI applied to real tasks.
- Models:
- - Russian Sensitive Topics Classifier: A model for detecting flammable/sensitive topics (e.g., racism, drugs, terrorism, etc.)
- - Russian Inappropriate Utterances Classifier: A model for detecting nontoxic but still inappropriate messages
- - Mutual Implication Score: A symmetric measure of text semantic similarity based on a RoBERTA model pretrained for natural language inference and fine-tuned on a paraphrase detection dataset
- - GenChal_2022_nigula: A model (details not provided)
Research Experience
- Recent research involved toxicity detection and text style transfer.
Education
- Ph.D. student at the University of Santiago de Compostela.
Background
- Research Interests: NLP and Explainable AI. Current research is on Natural Language Generation for Bayesian Networks reasoning explanation. Recent research was dedicated to toxicity detection and text style transfer.
Miscellany
- You can reach him via Telegram @bbkjunior or by email at bbkhse@gmail.com or nikolay.babakov@usc.es.
