Papers › Improving Results on Russian Sentiment Datasets

Improving Results on Russian Sentiment Datasets

28 Jul 2020arXiv:2007.14310archive 2025-07-28

Anton Golubev, Natalia Loukachevitch

In this study, we test standard neural network architectures (CNN, LSTM, BiLSTM) and recently appeared BERT architectures on previous Russian sentiment evaluation datasets. We compare two variants of Russian BERT and show that for all sentiment tasks in this study the conversational variant of Russian BERT performs better. The best results were achieved by BERT-NLI model, which treats sentiment classification tasks as a natural language inference task. On one of the datasets, this model practically achieves the human level.

Paper PDF Code

Code

antongolubev5/Targeted-SA-for-Russian-Datasets officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Natural Language Inference Sentiment Analysis Sentiment Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam Attention Attention Dropout BERT Dense Connections Dropout LSTM Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Sigmoid Activation Softmax Tanh Activation Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections