Edit model card


このモデルはluke-japanese-largeを yahoo japan/JGLUEのJCommonsenseQA( https://github.com/yahoojapan/JGLUE ) を用いてファインチューニングしたものです。


This model is fine-tuned model for commonsenseqa which is based on luke-japanese-large

This model is fine-tuned by using yahoo japan JGLUE JCommonsenseQA dataset.

You could use this model for commonsenseqa tasks.

モデルの精度 accuracy of model

モデルの精度は 83.82484361036744 でした。他の言語モデルと比べても非常に高い値となっています。 (参考 BERT:72.0、XLM RoBERTa base:68.7)

How to use 使い方

transformers, sentencepieceをinstallして、以下のコードを実行することで、commonsenseqaタスクを解かせることができます。 please execute this code.

from transformers import AutoTokenizer, AutoModelForMultipleChoice
import torch
import numpy as np

# modelのロード
tokenizer = AutoTokenizer.from_pretrained('Mizuiro-sakura/luke-large-commonsenseqa-japanese')
model = AutoModelForMultipleChoice.from_pretrained('Mizuiro-sakura/luke-large-commonsenseqa-japanese')

# 質問と選択肢の代入
question = '電子機器で使用される最も主要な電子回路基板の事をなんと言う?'
choice1 = '掲示板'
choice2 = 'パソコン'
choice3 = 'マザーボード'
choice4 = 'ハードディスク'
choice5 = 'まな板'

# トークン化(エンコーディング・形態素解析)する
token = tokenizer([question,question,question,question,question],[choice1,choice2,choice3,choice4,choice5],return_tensors='pt',padding=True)

# modelに入力するための下準備
X1 = np.empty(shape=(1, 5, leng))
X2 = np.empty(shape=(1, 5, leng))
X1[0, :, :] = token['input_ids']
X2[0, :, :] = token['attention_mask']

# modelにトークンを入力する
results = model(torch.tensor(X1).to(torch.int64),torch.tensor(X2).to(torch.int64))

# 最も高い値のインデックスを取得する

what is Luke? Lukeとは?[1]

LUKE (Language Understanding with Knowledge-based Embeddings) is a new pre-trained 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. LUKE adopts an entity-aware self-attention mechanism that is an extension of the self-attention mechanism of the transformer, and considers the types of tokens (words or entities) when computing attention scores.

LUKE achieves state-of-the-art results on five popular NLP benchmarks including SQuAD v1.1 (extractive question answering), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), TACRED (relation classification), and Open Entity (entity typing). luke-japaneseは、単語とエンティティの知識拡張型訓練済み Transformer 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。

Acknowledgments 謝辞

Lukeの開発者である山田先生とStudio ousiaさんには感謝いたします。 I would like to thank Mr.Yamada @ikuyamada and Studio ousia @StudioOusia.


[1]@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} }

Downloads last month
Inference API (serverless) does not yet support transformers models for this pipeline type.