keyT5-large Open-source Text-to-Keyword Model - Accurately Extract Keywords from Russian Texts for Free

Keyt5 Large

Developed by 0x7o

keyT5 is a text-to-keyword model based on the T5 architecture, primarily used for extracting keywords from Russian text.

Large Language Model

Transformers

OtherOpen Source License:MIT #Russian keyword extraction #T5 text generation #News summarization

Downloads 195

Release Time : 3/2/2022

Model Overview

This model can automatically extract key terms and phrases from input Russian text, generating a semicolon-separated keyword list. It supports both large and base versions, suitable for scenarios such as information retrieval and content analysis.

Model Features

Russian keyword extraction

Keyword extraction capability optimized specifically for Russian text.

Multi-version support

Offers both large and base model versions to meet different computational resource needs.

Easy to use

Obtain keyword lists through simple API calls.

Model Capabilities

Russian text processing

Automatic keyword extraction

Text content analysis

Use Cases

News analysis

News keyword extraction

Extract key terms and events from news reports

Generate keyword lists representing news topics.

Content management

Document tag generation

Automatically generate tags and classification keywords for documents

Improve document retrieval and organization efficiency.

🚀 keyT5. Large version

keyT5 Large is a model designed for text-to-keyword extraction, supporting the Russian language. It can efficiently extract keywords from text, helping users quickly capture the core information of the text.

Supported Languages

Russian

🚀 Quick Start

💻 Usage Examples

Basic Usage

The following code demonstrates how to use the keyT5 model to extract keywords from text. The code returns a list of keywords, and duplicates may exist.

from itertools import groupby
import torch
from transformers import T5ForConditionalGeneration, T5Tokenizer
model_name = "0x7194633/keyt5-large" # or 0x7194633/keyt5-base
tokenizer = T5Tokenizer.from_pretrained(model_name)
model = T5ForConditionalGeneration.from_pretrained(model_name)

def generate(text, **kwargs):
    inputs = tokenizer(text, return_tensors='pt')
    with torch.no_grad():
        hypotheses = model.generate(**inputs, num_beams=5, **kwargs)
    s = tokenizer.decode(hypotheses[0], skip_special_tokens=True)
    s = s.replace('; ', ';').replace(' ;', ';').lower().split(';')[:-1]
    s = [el for el, _ in groupby(s)]
    return s

article = """Reuters сообщил об отмене 3,6 тыс. авиарейсов из-за «омикрона» и погоды
Наибольшее число отмен авиарейсов 2 января пришлось на американские авиакомпании 
SkyWest и Southwest, у каждой — более 400 отмененных рейсов. При этом среди 
отмененных 2 января авиарейсов — более 2,1 тыс. рейсов в США. Также свыше 6400 
рейсов были задержаны."""

print(generate(article, top_p=1.0, max_length=64))  
# ['авиаперевозки', 'отмена авиарейсов', 'отмена рейсов', 'отмена авиарейсов', 'отмена рейсов', 'отмена авиарейсов']

📦 Installation

Before using the model, you need to install the necessary dependencies. You can use the following command to install:

pip install transformers sentencepiece

📚 Documentation

🚀 Training

If you want to train the model yourself, you can go to the training notebook to learn more:

📄 License

This project is licensed under the MIT license.

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