Inquisitive Question Generation for High Level Text Comprehension
This addresses the problem of automated question generation for text comprehension, but it is incremental as it builds on existing datasets and models.
The authors tackled the challenge of generating high-level comprehension questions from text, which is difficult for current models, by introducing the INQUISITIVE dataset of ~19K questions and showing that a GPT-2-based model can generate reasonable questions, though the task remains challenging.
Inquisitive probing questions come naturally to humans in a variety of settings, but is a challenging task for automatic systems. One natural type of question to ask tries to fill a gap in knowledge during text comprehension, like reading a news article: we might ask about background information, deeper reasons behind things occurring, or more. Despite recent progress with data-driven approaches, generating such questions is beyond the range of models trained on existing datasets. We introduce INQUISITIVE, a dataset of ~19K questions that are elicited while a person is reading through a document. Compared to existing datasets, INQUISITIVE questions target more towards high-level (semantic and discourse) comprehension of text. We show that readers engage in a series of pragmatic strategies to seek information. Finally, we evaluate question generation models based on GPT-2 and show that our model is able to generate reasonable questions although the task is challenging, and highlight the importance of context to generate INQUISITIVE questions.