BERT for Russian news clustering
S. V. Khaustov, N. E. Gorlova, A. V Kalmykov, A. S. Kabaev, MTS AI Moscow, Russia · Computational Linguistics and Intellectual Technologies · 2021
This paper provides results of participation in the Russian News Clustering task within Dialogue Evaluation 2021.News clustering is a common task in the industry, and its purpose is to group news by events.We propose two methods based on BERT for news clustering, one of them shows competitive results in Dialogue 2021 evaluation.The first method uses supervised representation learning.The second one reduces the problem to binary classification.