Summarization Hi Mbart Large 50 Hungarian

🚀 Hungarian Abstractive Summarization with finetuned MBart-50 model

This project uses a finetuned MBart - 50 model for Hungarian abstractive summarization, offering a practical solution for text summarization tasks in Hungarian.

🚀 Quick Start

For further details, see or our demo site.

✨ Features

• Finetuned on mBART - large - 50 model.
• Finetuned on HI corpus (hvg.hu + index.hu), with 559162 segments.

📚 Documentation

Limitations

• tokenized input text (tokenizer: HuSpaCy).
• max_source_length = 1024.
• max_target_length = 256.

Results

💻 Usage Examples

Basic Usage

from transformers import pipeline

summarization = pipeline(task="summarization", model="NYTK/summarization-hi-mbart-large-50-hungarian")

print(summarization(input_text)[0]["summary_text"])

📄 License

This project is under the MIT license.

📚 Citation

If you use this model, please cite the following paper:

@inproceedings {yang-multi-sum,
    title = {{Többnyelvű modellek és PEGASUS finomhangolása magyar nyelvű absztraktív összefoglalás feladatára}},
    booktitle = {XIX. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2023)},
    year = {2023},
    publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
    address = {Szeged, Magyarország},
    author = {Yang, Zijian Győző},
    pages = {381--393}
}