|
|
--- |
|
|
language: |
|
|
- "uk" |
|
|
tags: |
|
|
- "ukrainian" |
|
|
- "token-classification" |
|
|
- "pos" |
|
|
- "dependency-parsing" |
|
|
base_model: Goader/liberta-large-v2 |
|
|
datasets: |
|
|
- "universal_dependencies" |
|
|
license: "cc-by-4.0" |
|
|
pipeline_tag: "token-classification" |
|
|
--- |
|
|
|
|
|
# bert-large-ukrainian-ud-goeswith |
|
|
|
|
|
## Model Description |
|
|
|
|
|
This is a BERT model for POS-tagging and dependency-parsing (using `goeswith` for subwords), derived from [liberta-large-v2](https://huggingface.co/Goader/liberta-large-v2). |
|
|
|
|
|
## How to Use |
|
|
|
|
|
```py |
|
|
from transformers import pipeline |
|
|
nlp=pipeline("universal-dependencies","KoichiYasuoka/bert-large-ukrainian-ud-goeswith",trust_remote_code=True,aggregation_strategy="simple") |
|
|
print(nlp("Біжать алеї звуків, саджених у гами.")) |
|
|
``` |
|
|
|
|
|
|
