|
ADVANCED STUDIES IN ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
Incremental learning of topic models for finding trend topics in scientific publications
N. A. Gerasimenkoa, A. S. Chernyavskya, M. A. Nikiforovaa, M. D. Nikitina, K. V. Vorontsovb a Sberbank, Moscow, Russia
b Federal Research Center "Computer Science and Control" of Russian Academy of Sciences, Moscow, Russia
Abstract:
With a soaring number of scientific publications and rapid emergence of new directions and approaches, the scientific community faces the task of timely identification of trends. By a trend, we mean a semantically homogeneous topic characterized by a steady lexical kernel and a sharp, often exponential increase in the number of publications [1]. Examples of trends in machine learning are “LSTM”, “deep learning”, “word2vec”, “BERT”, and “fake news detection”. For real-time detection of trend topics from a stream of scientific publications, we use incremental methods of probabilistic topic modeling. An ARTM-based approach to early trend detection has been shown to outperform popular classical and neural network approaches to this task. A dataset of 91 trends for performance evaluation has been manually collected and made available for public use.
Keywords:
incremental topic modeling, detection of research trends, ARTM.
Citation:
N. A. Gerasimenko, A. S. Chernyavsky, M. A. Nikiforova, M. D. Nikitin, K. V. Vorontsov, “Incremental learning of topic models for finding trend topics in scientific publications”, Dokl. RAN. Math. Inf. Proc. Upr., 508 (2022), 106–108; Dokl. Math., 106:suppl. 1 (2022), S97–S98
Linking options:
https://www.mathnet.ru/eng/danma346 https://www.mathnet.ru/eng/danma/v508/p106
|
Statistics & downloads: |
Abstract page: | 69 | References: | 14 |
|