luke-japanese-base / README.md
ikuyamada's picture
Initial commit
29167de
|
raw
history blame
2.32 kB
---
language: ja
thumbnail: https://github.com/studio-ousia/luke/raw/master/resources/luke_logo.png
tags:
- luke
- named entity recognition
- entity typing
- relation classification
- question answering
license: apache-2.0
---
## luke-japanese
**luke-japanese** is the Japanese version of **LUKE** (**L**anguage
**U**nderstanding with **K**nowledge-based **E**mbeddings), a pre-trained
_knowledge-enhanced_ contextualized representation of words and entities based
on transformer. LUKE treats words and entities in a given text as independent
tokens, and outputs contextualized representations of them. Please refer to our
[GitHub repository](https://github.com/studio-ousia/luke) for more details and
updates.
**luke-japanese**は、単語とエンティティの知識拡張型訓練済みモデル**LUKE**の日本
語版です。LUKE は単語とエンティティを独立したトークンとして扱い、これらの文脈を
考慮した表現を出力します。詳細については
、[GitHub リポジトリ](https://github.com/studio-ousia/luke)を参照してください。
### Experimental results on JGLUE
The performance of luke-japanese evaluated on the dev set of
[JGLUE](https://github.com/yahoojapan/JGLUE) is shown as follows:
| Model | MARC-ja | JSTS | JNLI | JCommonsenseQA |
| ---------------------- | --------- | ------------------- | --------- | -------------- |
| | acc | Pearson/Spearman | acc | acc |
| **luke-japanese-base** | **0.963** | **0.912**/**0.875** | **0.912** | **0.842** |
| _Baselines:_ | |
| Tohoku BERT base | 0.958 | 0.899/0.859 | 0.899 | 0.808 |
| NICT BERT base | 0.958 | 0.903/0.867 | 0.902 | 0.823 |
| Waseda RoBERTa base | 0.962 | 0.901/0.865 | 0.895 | 0.840 |
| XLM RoBERTa base | 0.961 | 0.870/0.825 | 0.893 | 0.687 |
### Citation
```latex
@inproceedings{yamada2020luke,
title={LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention},
author={Ikuya Yamada and Akari Asai and Hiroyuki Shindo and Hideaki Takeda and Yuji Matsumoto},
booktitle={EMNLP},
year={2020}
}
```