The NarrativeQA Reading Comprehension Challenge

TLDR

Reading comprehension requires integrating information across an entire document, yet current datasets rely on superficial cues and fail to test deep integration. The authors introduce a dataset and tasks that require answering questions about stories by reading full books or movie scripts to promote deeper language comprehension. The tasks are structured to necessitate narrative understanding instead of shallow pattern matching. Human participants solve the tasks easily, whereas standard RC models perform poorly, highlighting the dataset’s difficulty and prompting further analysis.

Abstract

Reading comprehension (RC)—in contrast to information retrieval—requires integrating information and reasoning about events, entities, and their relations across a full document. Question answering is conventionally used to assess RC ability, in both artificial agents and children learning to read. However, existing RC datasets and tasks are dominated by questions that can be solved by selecting answers using superficial information (e.g., local context similarity or global term frequency); they thus fail to test for the essential integrative aspect of RC. To encourage progress on deeper comprehension of language, we present a new dataset and set of tasks in which the reader must answer questions about stories by reading entire books or movie scripts. These tasks are designed so that successfully answering their questions requires understanding the underlying narrative rather than relying on shallow pattern matching or salience. We show that although humans solve the tasks easily, standard RC models struggle on the tasks presented here. We provide an analysis of the dataset and the challenges it presents.