Topical Text Classification of Russian News: a Comparison of BERT and Standard Models
Author:
- 27 April 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 160-166
Abstract
The paper is devoted to the single-label topical classification of Russian news. The author compares the BERT features and standard character, word and structure-level features as text models. Experiments with OpenCorpora and eight news topics show that the BERT model is superior to standard ones, and achieves good classification quality for a small dataset of long news. Error analysis reveals the best classified topics: "economics", "culture", and "media". Comparison with the state-of-the-art research allows to consider BERT as a baseline for future investigations of analysis of texts in Russian.Keywords
This publication has 13 references indexed in Scilit:
- A Survey of Models for Constructing Text Features to Classify Texts in Natural Language2021
- Topical Classification of Text Fragments Accounting for Their Nearest ContextAutomation and Remote Control, 2020
- Text classification with semantically enriched word embeddingsNatural Language Engineering, 2020
- A Survey on News Classification Techniques2020
- Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks2020
- Hierarchical Transformers for Long Document Classification2019
- Application of Natural Language Processing Algorithms to the Task of Automatic Classification of Russian Scientific TextsData Science Journal, 2019
- An automated text categorization framework based on hyperparameter optimizationKnowledge-Based Systems, 2018
- DeepPavlov: Open-Source Library for Dialogue Systems2018
- Disconnected Recurrent Neural Networks for Text Categorization2018