| language: | |
| - "vi" | |
| tags: | |
| - "vietnamese" | |
| - "token-classification" | |
| - "pos" | |
| - "dependency-parsing" | |
| base_model: vinai/phobert-base | |
| datasets: | |
| - "universal_dependencies" | |
| license: "cc-by-sa-4.0" | |
| pipeline_tag: "token-classification" | |
| widget: | |
| - text: "Hai cái đầu thì tốt hơn một" | |
| # phobert-base-vietnamese-ud-goeswith | |
| ## Model Description | |
| This is a PhoBERT model pre-trained on Vietnamese texts for POS-tagging and dependency-parsing (using `goeswith` for subwords), derived from [phobert-base](https://huggingface.co/vinai/phobert-base). | |
| ## How to Use | |
| ```py | |
| from transformers import pipeline | |
| nlp=pipeline("universal-dependencies","KoichiYasuoka/phobert-base-vietnamese-ud-goeswith",trust_remote_code=True,aggregation_strategy="simple") | |
| print(nlp("Hai cái đầu thì tốt hơn một.")) | |
| ``` | |
| ## Reference | |
| Koichi Yasuoka: [Sequence-Labeling RoBERTa Model for Dependency-Parsing in Classical Chinese and Its Application to Vietnamese and Thai](https://doi.org/10.1109/ICBIR57571.2023.10147628), ICBIR 2023: 8th International Conference on Business and Industrial Research (May 2023), pp.169-173. | |