doi.bio/anna_potapenko
Anna Potapenko
Overview
Anna Potapenko is an AI researcher in language and biology. She is a PhD student at the National Research University Higher School of Economics, Moscow, in the Department of Computer Science. Her research interests include natural language processing and machine learning.
Education
- National Research University Higher School of Economics, Moscow – PhD (current)
Research
- Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning
- Learning and Evaluating Sparse Interpretable Sentence Embeddings
- Interpretable Probabilistic Embeddings: Bridging the Gap Between Topic Models and Neural Networks
- Additive Regularization of Topic Models for Topic Selection and Sparse Factorization
- Tutorial on Probabilistic Topic Modeling: Additive Regularization for Stochastic Matrix Factorization
Anna Potapenko
Overview
Anna Potapenko is an AI researcher in language and biology. She is a PhD student at the National Research University Higher School of Economics, Moscow, in the Department of Computer Science. Her research interests include natural language processing and machine learning.
Education
- National Research University Higher School of Economics, Moscow – PhD (current)
Research
- Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning
- Learning and Evaluating Sparse Interpretable Sentence Embeddings
- Interpretable Probabilistic Embeddings: Bridging the Gap Between Topic Models and Neural Networks
- Additive Regularization of Topic Models for Topic Selection and Sparse Factorization
- Tutorial on Probabilistic Topic Modeling: Additive Regularization for Stochastic Matrix Factorization
- Robust PLSA performs better than LDA
Anna Potapenko
Overview
Anna Potapenko is an AI researcher in language and biology. She is a PhD student at the National Research University Higher School of Economics in Moscow, specialising in computer science.
Research Focus
Potapenko's research focuses on natural language processing. Her previous research has included word embeddings and the interpretability of sentence embeddings. She has also worked on bridging the gap between topic models and neural networks, as well as additive regularisation of topic models for improved topic selection.
Publications
- Interpretable Probabilistic Embeddings: Bridging the Gap Between Topic Models and Neural Networks
- Learning and Evaluating Sparse Interpretable Sentence Embeddings
- Additive Regularization of Topic Models for Topic Selection and Sparse Factorization
- Tutorial on Probabilistic Topic Modeling: Additive Regularization for Stochastic Matrix Factorization
sness@sness.net