Mt5 Base HunSum 1

🚀 mT5-base-HunSum-1

The mT5-base-HunSum-1 is a Hungarian abstractive summarization model. It addresses the need for effective text summarization in Hungarian, leveraging the SZTAKI-HLT/HunSum-1 dataset for training and building upon the google/mt5-base architecture.

🚀 Quick Start

The mT5-base-HunSum-1 is a powerful tool for Hungarian text summarization. It was trained on the SZTAKI-HLT/HunSum-1 dataset and is based on google/mt5-base.

✨ Features

• Model Type: Text Summarization
• Language: Hungarian
• Resource for More Information: GitHub Repo

🔧 Technical Details

Parameters

• Batch Size: 12
• Learning Rate: 5e-5
• Weight Decay: 0.01
• Warmup Steps: 3000
• Epochs: 10
• no_repeat_ngram_size: 3
• num_beams: 5
• early_stopping: False
• encoder_no_repeat_ngram_size: 4

📚 Documentation

Results

📄 License

This model is licensed under the apache-2.0 license.

📚 Citation

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

@inproceedings {HunSum-1,
    title = {{HunSum-1: an Abstractive Summarization Dataset for Hungarian}},
	booktitle = {XIX. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2023)},
	year = {2023},
	publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
	address = {Szeged, Magyarország},
	author = {Barta, Botond and Lakatos, Dorina and Nagy, Attila and Nyist, Mil{\'{a}}n Konor and {\'{A}}cs, Judit},
	pages = {231--243}
}