| language: | |
| - "lzh" | |
| tags: | |
| - "classical chinese" | |
| - "literary chinese" | |
| - "ancient chinese" | |
| - "token-classification" | |
| - "pos" | |
| - "dependency-parsing" | |
| base_model: KoichiYasuoka/roberta-classical-chinese-base-char | |
| datasets: | |
| - "universal_dependencies" | |
| license: "apache-2.0" | |
| pipeline_tag: "token-classification" | |
| widget: | |
| - text: "孟子見梁惠王" | |
| # roberta-classical-chinese-base-ud-goeswith | |
| ## Model Description | |
| This is a RoBERTa model pre-trained on Classical Chinese texts for POS-tagging and dependency-parsing (using `goeswith` for subwords), derived from [roberta-classical-chinese-base-char](https://huggingface.co/KoichiYasuoka/roberta-classical-chinese-base-char) and [UD_Classical_Chinese-Kyoto](https://github.com/UniversalDependencies/UD_Classical_Chinese-Kyoto). | |
| ## How to Use | |
| ```py | |
| from transformers import pipeline | |
| nlp=pipeline("universal-dependencies","KoichiYasuoka/roberta-classical-chinese-base-ud-goeswith",trust_remote_code=True,aggregation_strategy="simple") | |
| print(nlp("孟子見梁惠王")) | |
| ``` | |
| ## 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. | |