| language: | |
| - "ko" | |
| tags: | |
| - "korean" | |
| - "token-classification" | |
| - "pos" | |
| - "dependency-parsing" | |
| base_model: KoichiYasuoka/roberta-base-korean-hanja | |
| datasets: | |
| - "universal_dependencies" | |
| license: "cc-by-sa-4.0" | |
| pipeline_tag: "token-classification" | |
| widget: | |
| - text: "홍시 맛이 나서 홍시라 생각한다." | |
| - text: "紅柹 맛이 나서 紅柹라 生覺한다." | |
| # roberta-base-korean-ud-goeswith | |
| ## Model Description | |
| This is a RoBERTa model pre-trained on Korean texts for POS-tagging and dependency-parsing (using `goeswith` for subwords), derived from [roberta-base-korean-hanja](https://huggingface.co/KoichiYasuoka/roberta-base-korean-hanja). | |
| ## How to Use | |
| ```py | |
| from transformers import pipeline | |
| nlp=pipeline("universal-dependencies","KoichiYasuoka/roberta-base-korean-ud-goeswith",trust_remote_code=True,aggregation_strategy="simple") | |
| print(nlp("홍시 맛이 나서 홍시라 생각한다.")) | |
| ``` | |