ruBert-tiny-questions-classifier Open-source Model - Free Deployment for Precise Classification of Russian Questions

Rubert Tiny Questions Classifier

Developed by Den4ikAI

This is a Russian question classification model based on ruBert-tiny, designed to distinguish between precise and imprecise questions.

Text Classification

Transformers

OtherOpen Source License:MIT #Russian question classification #Precise question identification #Imprecise question detection

Downloads 20

Release Time : 6/7/2023

Model Overview

The model categorizes Russian questions into two types: precise questions requiring definitive answers and imprecise questions allowing for discussion.

Model Features

Russian question classification

Accurately distinguishes between precise questions requiring factual answers and imprecise questions allowing open-ended discussion

Lightweight model

Based on ruBert-tiny architecture, suitable for deployment in resource-constrained environments

Model Capabilities

Russian text classification

Question type identification

Use Cases

Customer service

Automatic question routing

Automatically categorizes customer questions to relevant departments

Improves customer service efficiency and reduces manual classification time

Educational applications

Learning question analysis

Identifies student question types to provide appropriate response methods

Enhances the response quality of educational Q&A systems

🚀 Den4ikAI/ruBert-tiny-questions-classifier

This model classifies questions into two categories, providing a clear distinction between fact - seeking and open - ended questions.

🚀 Quick Start

The model classifies questions into two classes:

Exact question (exact_question) - A question that requires a clear, factual answer.
Inaccurate question (innacurate_question) - A question that allows for reasoning and philosophical exploration.

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

class RuBertQuestionClassifier:
    def __init__(self):
        self.device = torch.device("cpu")
        self.tokenizer = AutoTokenizer.from_pretrained("Den4ikAI/ruBert-tiny-questions-classifier")
        self.model = AutoModelForSequenceClassification.from_pretrained("Den4ikAI/ruBert-tiny-questions-classifier").to(
            self.device).eval()
        self.classes = ['exact_question', 'inaccurate_question']

    def get_question_type(self, text):
        text = text.lower().replace(',', '').replace('?', '')
        inputs = self.tokenizer(text, max_length=512, add_special_tokens=False, truncation=True,
                                return_tensors='pt').to(self.device)
        with torch.no_grad():
            logits = self.model(**inputs).logits
            probas = list(torch.sigmoid(logits)[0].cpu().detach().numpy())
        out = self.classes[probas.index(max(probas))]
        self.logger.debug('Mode: {}'.format(out))
        return out

classifier = RuBertQuestionClassifier()
print(classifier.get_question_type('когда я найду своего принца'))
print(classifier.get_question_type('что такое цианид'))

📄 License

This project is licensed under the MIT license.

📚 Documentation

Citation

@MISC{Den4ikAI/ruBert-tiny-questions-classifier,
    author  = {Denis Petrov},
    title   = {Russian question type classifier model},
    url     = {https://huggingface.co/Den4ikAI/ruBert-tiny-questions-classifier},
    year    = 2023
}

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご