paper-with-me

Papers

Transfer Learning for Improving Results on Russian Sentiment Datasets

2021-07-06 · 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 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.

📄 PDF Abstract BibTeX arXiv:2107.02499

Code (1)

antongolubev5/Auto-Dataset-For-Transfer-Learning 공식 구현

Tasks

Natural Language InferenceSentiment AnalysisSentiment ClassificationTransfer Learning

Similar Papers 제목 키워드 기반

Deep Transfer Learning Baselines for Sentiment Analysis in Russian

2021-07-01 · Sergey Smetanin, Mikhail Komarov

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 Learning

Improving Results on Russian Sentiment Datasets

2020-07-28 · 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 sho…

Natural Language InferenceSentiment AnalysisSentiment Classification

RuSentiment: An Enriched Sentiment Analysis Dataset for Social Media in Russian

2018-08-01 · COLING 2018 8 · Anna Rogers, Alexey Romanov, Anna Rumshisky, Svitlana Volkova 외

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 Embeddings

Creating a General Russian Sentiment Lexicon

2016-05-01 · LREC 2016 5 · Natalia Loukachevitch, Anatolii Levchik

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

2019-05-17 · Yuri Kuratov, Mikhail Arkhipov

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