Hyeoni
/

Question-Generation-Multitask-Korquad

Model card Files Files and versions Community

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Question Generation Model with KorQuAD

This model is a fine-tuend version of paust/pko-t5-base on the KorQuAD v1.0 Dataset.

Dataset

KorQuAD v1.0 Dataset (csv)
Train
Valid

Train

30% 확률로 input answer 대신 '[MASK]'를 넣어 질문 문장을 생성하도록 학습한다.
그 결과, input answer가 없을 때도 적절히 answer을 찾아 질문을 생성할 수 있다.

Question Generation without Input Answer

context = """ CONTEXT """
input_answer = '[MASK]'
        
generated = generate(best_model, input_answer, context)
        
show_result(generated)

References

Leaf-Question-Generation :https://github.com/KristiyanVachev/Leaf-Question-Generation
pko-t5-base : https://huggingface.co/paust/pko-t5-base
KorQuAD v1.0 : https://korquad.github.io/KorQuad%201.0/

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.