Instructions to use kit-nlp/bert-base-japanese-sentiment-irony with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kit-nlp/bert-base-japanese-sentiment-irony with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="kit-nlp/bert-base-japanese-sentiment-irony")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("kit-nlp/bert-base-japanese-sentiment-irony") model = AutoModelForSequenceClassification.from_pretrained("kit-nlp/bert-base-japanese-sentiment-irony") - Notebooks
- Google Colab
- Kaggle
BERT Base Japanese for Irony
This is a BERT Base model for sentiment analysis in Japanese additionally finetuned for automatic irony detection.
The model was based on bert-base-japanese-sentiment, and later finetuned on a dataset containing ironic and sarcastic tweets.
Licenses
The finetuned model with all attached files is licensed under CC BY-SA 4.0, or Creative Commons Attribution-ShareAlike 4.0 International License.
Citations
Please, cite this model using the following citation.
@inproceedings{dan2022bert-base-irony02,
title={北見工業大学 テキスト情報処理研究室 ELECTRA Base 皮肉検出モデル (daigo ver.)},
author={団 俊輔 and プタシンスキ ミハウ and ジェプカ ラファウ and 桝井 文人},
publisher={HuggingFace},
year={2022},
url = "https://huggingface.co/kit-nlp/bert-base-japanese-sentiment-irony"
}
- Downloads last month
- 106
