StoryQA: Story Grounded Question Answering DatasetDownload PDF

Anonymous

08 Mar 2022 (modified: 05 May 2023)NAACL 2022 Conference Blind SubmissionReaders: Everyone
Paper Link: https://openreview.net/forum?id=oPtnaks3Q6
Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)
Abstract: The abundance of benchmark datasets supports the recent trend of increased attention given to Question Answering (QA) tasks. However, most of them lack a diverse selection of QA types and more challenging questions. In this work, we present StoryQA, a new task and dataset addressing diverse QA problems for both in-context and out-of-context questions. Additionally, we developed QA models based on large pretrained language models. Our experiments on the new dataset show our developed model achieves comparable performance to answers provided by humans. The resources in this work will be released to foster future research.
0 Replies

Loading