The NarrativeQA Reading Comprehension Challenge
This addresses the need for deeper language comprehension in AI, offering a new benchmark to move beyond superficial pattern matching in reading comprehension tasks.
The authors tackled the problem of shallow reading comprehension in AI by introducing the NarrativeQA dataset, which requires understanding entire narratives from books or movie scripts, and found that standard models struggle while humans perform easily.
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.