A Feasibility Study of Answer-Agnostic Question Generation for Education

Autor:	Dugan, Liam, Miltsakaki, Eleni, Upadhyay, Shriyash, Ginsberg, Etan, Gonzalez, Hannah, Choi, Dayheon, Yuan, Chuning, Callison-Burch, Chris
Rok vydání:	2022
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Human-Computer Interaction I.2.7
Druh dokumentu:	Working Paper
Popis:	We conduct a feasibility study into the applicability of answer-agnostic question generation models to textbook passages. We show that a significant portion of errors in such systems arise from asking irrelevant or uninterpretable questions and that such errors can be ameliorated by providing summarized input. 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% $\rightarrow$ 83%) as determined by expert annotators. We also find that, in the absence of human-written summaries, automatic summarization can serve as a good middle ground. Comment: To be published in 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2203.08685 Zobrazit plný text záznamu View this record from Arxiv