PathQG: Neural Question Generation from Facts
EMNLP 2020, pp. 9066-9075, 2020.
Existing research for question generation encodes the input text as a sequence of tokens without explicitly modeling fact information. These models tend to generate irrelevant and uninformative questions. In this paper, we explore to incorporate facts in the text for question generation in a comprehensive way. We present a novel task of q...More
Full Text (Upload PDF)
PPT (Upload PPT)