Additive regularizarion of topic models with fast text vectorizartion
2020Journal articleIlya Aleksandrovich Irkhin, Victor Gennadyevich Bulatov, Константин Вячеславович Воронцов
Computer Research and Modeling
260 results
2020·Journal article·Ilya Aleksandrovich Irkhin, Victor Gennadyevich Bulatov, Константин Вячеславович Воронцов
Computer Research and Modeling
2020·Conference paper·Eugeniia Veselova, Константин Вячеславович Воронцов
2020·Journal article·Anastasia Ianina, Константин Вячеславович Воронцов
International Journal of Embedded and Real-Time Communication Systems
2020·Conference paper·Murat Apishev, Константин Вячеславович Воронцов
2019·Conference paper·Daria Soboleva, Константин Вячеславович Воронцов
EPiC series in language and linguistics
2019·Conference paper·Evgeny Egorov, Filipp Nikitin, Vasiliy Alekseev, Alexey Goncharov +1
2019·Conference paper·Anastasia Ianina, Константин Вячеславович Воронцов
2019·Conference paper·AITHEA, Russia, Maksim Eremeev, Константин Вячеславович Воронцов
2018·Other·Anastasia Ianina, Lev Golitsyn, Константин Вячеславович Воронцов
Communications in computer and information science
2017·Preprint·Potapenko, Anna, Popov, Artem, Константин Вячеславович Воронцов
arXiv (Cornell University)
We consider probabilistic topic models and more recent word embedding\ntechniques from a perspective of learning hidden semantic representations.\nInspired by a striking similarity of the two approaches, we merge them and\nlearn probabilistic embeddings with online EM-algorithm on word co-occurrence\ndata. The resulting embeddings perform on par with Skip-Gram Negative Sampling\n(SGNS) on word similarity tasks and benefit in the interpretability of the\ncomponents. Next, we learn probabilistic document embeddings that outperform\nparagraph2vec on a document similarity task and require less memory and time\nfor training. Finally, we employ multimodal Additive Regularization of Topic\nModels (ARTM) to obtain a high sparsity and learn embeddings for other\nmodalities, such as timestamps and categories. We observe further improvement\nof word similarity performance and meaningful inter-modality similarities.\n
2017·Conference paper·Anna Potapenko, Artem Popov, Константин Вячеславович Воронцов
Communications in computer and information science
2017·Conference paper·Murat Apishev, Sergei Koltcov, Olessia Koltsova, Sergey Nikolenko +1
Lecture notes in computer science
2017·Conference paper·Anastasia Ianina, Lev Golitsyn, Константин Вячеславович Воронцов
Communications in computer and information science
2017·Conference paper·Denis Kochedykov, Murat Apishev, Lev Golitsyn, Константин Вячеславович Воронцов
2016·Journal article·Murat Apishev, Sergei Koltcov, Olessia Koltsova, Sergey Nikolenko +1
Computación y Sistemas
2015·Book chapter·V. USPENSKIY, Константин Вячеславович Воронцов, V. TSELYKH, V. BUNAKOV
Series on advances in mathematics for applied sciences
2015·Conference paper·Константин Вячеславович Воронцов, Anna Potapenko, Alexander Plavin
Lecture notes in computer science
2015·Conference paper·Константин Вячеславович Воронцов, Oleksandr Frei, Murat Apishev, Peter Romov +2
2015·Conference paper·Константин Вячеславович Воронцов, Oleksandr Frei, Murat Apishev, Peter Romov +1
Communications in computer and information science
2014·Conference paper·Константин Вячеславович Воронцов, Anna Potapenko
Communications in computer and information science