Contrastive Multi-document Question Generation

8 Nov 2019Woon Sang ChoYizhe ZhangSudha RaoAsli CelikyilmazChenyan XiongJianfeng GaoMengdi WangBill Dolan

Multi-document question generation focuses on generating a question that covers the common aspect of multiple documents. However, models trained only using the targeted ("positive") document set generate questions that are generic i.e. they cover a larger scope than delineated by the document set... (read more)

PDF Abstract


No code implementations yet. Submit your code now

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.