2 papers
cs.CL2021
Transfer Learning for Improving Results on Russian Sentiment Datasets
Anton Golubev, Natalia Loukachevitch
In this study, we test transfer learning approach on Russian sentiment benchmark datasets using additional train sample created with distant supervision technique. We compare sever…
cs.CL2020
Improving Results on Russian Sentiment Datasets
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 comp…