---
language:
- "la"
tags:
- "latin"
- "token-classification"
- "pos"
- "dependency-parsing"
base_model: ClassCat/roberta-base-latin-v2
datasets:
- "universal_dependencies"
license: "cc-by-sa-4.0"
pipeline_tag: "token-classification"
widget:
- text: "deus videt te non sentientem"
---

# roberta-base-latin-ud-goeswith

## Model Description

This is a RoBERTa model pre-trained on CC-100 Latin texts for POS-tagging and dependency-parsing (using `goeswith` for subwords), derived from [roberta-base-latin-v2](https://huggingface.co./ClassCat/roberta-base-latin-v2).

## How to Use

```py
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/roberta-base-latin-ud-goeswith",trust_remote_code=True,aggregation_strategy="simple")
print(nlp("deus videt te non sentientem"))
```