---
language:
- "ain"
tags:
- "ainu"
- "token-classification"
- "pos"
- "dependency-parsing"
base_model: KoichiYasuoka/deberta-base-ainu-upos
license: "cc-by-sa-4.0"
pipeline_tag: "token-classification"
widget:
- text: "itak=as awa pon rupne aynu ene itaki"
- text: "イタカㇱ アワ ポン ルㇷ゚ネ アイヌ エネ イタキ"
- text: "итакас ава пон рубне айну эне итакі"
---

# deberta-base-ainu-ud-goeswith

## Model Description

This is a DeBERTa(V2) model pre-trained on Ainu texts (in カタカナ, Roman, and Кириллица) for POS-tagging and dependency-parsing (using `goeswith` for subwords), derived from [deberta-base-ainu-upos](https://huggingface.co/KoichiYasuoka/deberta-base-ainu-upos).

## How to Use

```
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/deberta-base-ainu-ud-goeswith",trust_remote_code=True,aggregation_strategy="simple")
print(nlp("itak=as awa pon rupne aynu ene itaki"))
```

## Reference

安岡孝一: [ローマ字・カタカナ・キリル文字併用アイヌ語RoBERTa・DeBERTaモデルの開発](http://id.nii.ac.jp/1001/00224072/), 情報処理学会研究報告, Vol.2023-CH-131『人文科学とコンピュータ』, No.7 (2023年2月18日), pp.1-7.