Transfer Learning for Improving Results on Russian Sentiment Datasets
In this study, we test transfer learning approach on Russian sentiment benchmark datasets using additional train sample created with distant supervision technique. We compare several variants of combining additional data with benchmark train samples. The best results were achieved using three-step approach of sequential training on general, thematic and original train samples. For most datasets, the results were improved by more than 3% to the current state-of-the-art methods. The BERT-NLI model treating sentiment classification problem as a natural language inference task reached the human level of sentiment analysis on one of the datasets.
Code (1)
Tasks
Natural Language InferenceSentiment AnalysisSentiment ClassificationTransfer LearningSimilar Papers 제목 키워드 기반
Deep Transfer Learning Baselines for Sentiment Analysis in Russian
Recently, transfer learning from pre-trained language models has proven to be effective in a variety of natural language processing tasks, including sentiment analysis. This paper aims at identifying deep transfer learni…
SentenceSentiment AnalysisTransfer LearningImproving Results on Russian Sentiment Datasets
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 sho…
Natural Language InferenceSentiment AnalysisSentiment ClassificationRuSentiment: An Enriched Sentiment Analysis Dataset for Social Media in Russian
This paper presents RuSentiment, a new dataset for sentiment analysis of social media posts in Russian, and a new set of comprehensive annotation guidelines that are extensible to other languages. RuSentiment is currentl…
Active LearningGeneral ClassificationSentiment AnalysisWord EmbeddingsCreating a General Russian Sentiment Lexicon
The paper describes the new Russian sentiment lexicon - RuSentiLex. The lexicon was gathered from several sources: opinionated words from domain-oriented Russian sentiment vocabularies, slang and curse words extracted fr…
Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language
The paper introduces methods of adaptation of multilingual masked language models for a specific language. Pre-trained bidirectional language models show state-of-the-art performance on a wide range of tasks including re…
Natural Language InferenceParaphrase IdentificationQuestion AnsweringReading Comprehension+2