You can deploy this model and start earning money today!

clarin-pl/
combo-nlp-xlm-roberta-base-portuguese-petrogold-ud2.17

Name: combo-nlp-xlm-roberta-base-portuguese-petrogold-ud2.17
Availability: InStock

pytorch

dependency-parsing

combo

universal-dependencies

token-classification

universal_dependencies

cc-by-sa-4.0

Views

No views yet

COMBO-NLP Model for Portuguese

Model Description

This is a Portuguese-language model based on combo-nlp, an open-source natural language preprocessing system. It performs:

sentence segmentation (via combo-seg)
tokenisation (via combo-seg)
part-of-speech tagging
morphological analysis
lemmatisation
dependency parsing

The Portuguese model uses FacebookAI/xlm-roberta-base as its base encoder and is trained on UD_Portuguese-PetroGold (UD v2.17).

Evaluation

Evaluation was performed on the UD_Portuguese-PetroGold test split using the standard CoNLL 2018 eval script.

Two evaluation rows are reported:

Full-text (F1): raw text is segmented by combo-seg, then parsed and compared against gold — measures end-to-end pipeline performance including segmentation quality.
Aligned accuracy: accuracy on correctly segmented (aligned) tokens — measures parsing quality on tokens that were correctly identified by the segmenter.

Morphosyntactic Tagging

Metric	Tokens	Sentences	Words	UPOS	XPOS	UFeats	AllTags	Lemmas
Full-text (F1)	99.72	96.76	98.44	97.61	98.44	97.14	96.70	97.87
Aligned accuracy	0.00	0.00	0.00	99.16	100.00	98.68	98.24	99.43

Dependency Parsing

Metric	UAS	LAS	CLAS	MLAS	BLEX
Full-text (F1)	92.75	91.64	88.98	85.25	88.35
Aligned accuracy	94.22	93.10	90.32	86.53	89.68

Usage

Install the library from PyPI (assuming you have a virtual environment created):

pip install combo-nlp

The combo-seg segmenter (used to split and tokenise raw text) is installed automatically as a dependency of combo-nlp, so no extra install step is needed.

python

from combo import COMBO

# Load a pre-trained model with the corresponding combo-seg segmenter
nlp = COMBO("Portuguese")

# Parse raw text (handles sentence splitting + tokenization)
result = nlp("A rápida raposa marrom pula sobre o cão preguiçoso.")

# Inspect results
for sentence in result:
    for token in sentence:
        print(f"{token.form:<15} {token.lemma:<15} {token.upos:<8} head={token.head}  {token.deprel}")

Refer to the combo-nlp documentation for installation and usage instructions:

License

The training data license: cc-by-sa-4.0 is derived from the Universal Dependencies treebank. For the full license terms of each treebank, please refer to the corresponding LICENSE.txt file in the treebank repository:

UD_Portuguese-PetroGold LICENSE.txt

Citation

If you use this model, please cite:

Ulewicz, M., Jabłońska, M., Klimaszewski, M., Przybyła, P., Pszenny, Ł., Rybak, P., Wiącek, M., & Wróblewska, A. (2026). COMBO-NLP Models Trained on UD v2.17. Zenodo. https://doi.org/10.5281/zenodo.19650523

bibtex

@software{combo_nlp_2026,
  author    = {Ulewicz, Michał and Jabłońska, Maja and Klimaszewski, Mateusz and Przybyła, Piotr and Pszenny, Łukasz and Rybak, Piotr and Wiącek, Martyna and Wróblewska, Alina},
  title     = {{COMBO-NLP} Models Trained on {UD} v2.17},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.19650523},
  url       = {https://doi.org/10.5281/zenodo.19650523}
}

Treebank References

If you use the Portuguese PetroGold treebank data, please also cite: