GaborMadarasz/ModernBERT-base-hungarian-POS

Model Card for Model ID

Hungarian Part-of-speech tagger ModernBERT-base.

Model Description

The model performs POS tagging on long Hungarian texts. (8k context-window)

labels: ['ADJ', 'ADP', 'ADV', 'AUX', 'CCONJ', 'DET', 'INTJ', 'NOUN', 'NUM', 'PART', 'PRON', 'PROPN', 'PUNCT', 'SCONJ', 'VERB', 'X']

Accuracy on hu_szeged-ud-test (token-level): 87.6%

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: Gábor Madarász
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: GaborMadarasz/ModernBERT-base-hungarian

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

Phase-1 finetune

UD Hungarian Szeged: https://universaldependencies.org/treebanks/hu_szeged/index.html

POS tagging performed with huSapcy (hu_core_news_lg) on Hungarian Wikipedia.

Phase-2 finetune

POS tagging performed with phase-1 fine-tuned ModernBERT on a subset of opensubtitles.

Training Hyperparameters

• Training regime: fp32

Metrics

Accuracy: 87.6

Results

[More Information Needed]

Model Card Contact

[email protected]