Instructions to use NYTK/summarization-hi-bart-hungarian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NYTK/summarization-hi-bart-hungarian with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="NYTK/summarization-hi-bart-hungarian")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("NYTK/summarization-hi-bart-hungarian") model = AutoModelForSeq2SeqLM.from_pretrained("NYTK/summarization-hi-bart-hungarian") - Notebooks
- Google Colab
- Kaggle
Hungarian Abstractive Summarization BART model
For further models, scripts and details, see our repository or our demo site.
- BART base model (see Results Table - bold):
- Pretrained on Webcorpus 2.0
- Finetuned HI corpus (hvg.hu + index.hu)
- Segments: 559.162
Limitations
- tokenized input text (tokenizer: HuSpaCy)
- max_source_length = 512
- max_target_length = 256
Results
| Model | HI | NOL |
|---|---|---|
| BART-base-512 | 30.18/13.86/22.92 | 46.48/32.40/39.45 |
| BART-base-1024 | 31.86/14.59/23.79 | 47.01/32.91/39.97 |
Citation
If you use this model, please cite the following paper:
@inproceedings {yang-bart,
title = {{BARTerezzünk! - Messze, messze, messze a világtól, - BART kísérleti modellek magyar nyelvre}},
booktitle = {XVIII. Magyar Számítógépes Nyelvészeti Konferencia},
year = {2022},
publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
address = {Szeged, Magyarország},
author = {Yang, Zijian Győző},
pages = {15--29}
}
- Downloads last month
- 45