Filters








1 Hit in 2.0 sec

A Feasibility Study of Answer-Agnostic Question Generation for Education [article]

Liam Dugan, Eleni Miltsakaki, Shriyash Upadhyay, Etan Ginsberg, Hannah Gonzalez, Dayheon Choi, Chuning Yuan, Chris Callison-Burch
2022 arXiv   pre-print
We find that giving these models human-written summaries instead of the original text results in a significant increase in acceptability of generated questions (33 annotators.  ...  We conduct a feasibility study into the applicability of answer-agnostic question generation models to textbook passages.  ...  Onestop QAmaker: Extract question-answer a great starting point for our experiments. We’re pairs from text in a one-stop approach.  ... 
arXiv:2203.08685v2 fatcat:aaynroe5vba5xe3ibqttcmluoy