Rubert Base Cased Sentiment

🚀 RuBERT for Sentiment Analysis

This model is designed for sentiment classification of short Russian texts.

This is a DeepPavlov/rubert-base-cased-conversational model trained on an aggregated corpus of 351,797 texts.

✨ Features

Labels

🚀 Quick Start

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoModelForSequenceClassification
from transformers import BertTokenizerFast

tokenizer = BertTokenizerFast.from_pretrained('blanchefort/rubert-base-cased-sentiment')
model = AutoModelForSequenceClassification.from_pretrained('blanchefort/rubert-base-cased-sentiment', return_dict=True)

@torch.no_grad()
def predict(text):
    inputs = tokenizer(text, max_length=512, padding=True, truncation=True, return_tensors='pt')
    outputs = model(**inputs)
    predicted = torch.nn.functional.softmax(outputs.logits, dim=1)
    predicted = torch.argmax(predicted, dim=1).numpy()
    return predicted

📚 Documentation

Datasets used for model training

• RuTweetCorp

  Rubtsova, Yu. Automatic Construction and Analysis of a Corpus of Short Texts (Microblog Posts) for the Development and Training of a Tone Classifier // Knowledge Engineering and Semantic Web Technologies. – 2012. – Vol. 1. – Pp. 109-116.

• RuReviews

  RuReviews: An Automatically Annotated Sentiment Analysis Dataset for Product Reviews in Russian.

• RuSentiment

  A. Rogers, A. Romanov, A. Rumshisky, S. Volkova, M. Gronas, A. Gribov. RuSentiment: An Enriched Sentiment Analysis Dataset for Social Media in Russian. Proceedings of COLING 2018.

• Reviews of medical institutions

  This dataset contains user reviews of medical institutions. It was collected in May 2019 from the website prodoctorov.ru.