arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.14336cs.IR
收藏

文档集合视觉问答

Document Collection Visual Question Answering

Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny

AI总结:

针对现有文档理解将文档作为单一元素处理的问题,提出DocCVQA新数据集与任务,要求模型对整个文档图像集合进行问答并检索相关文档,同时提出新评估指标和基线。

摘要:

当前文档理解的任务和方法旨在将文档作为单一元素进行处理。然而,文档通常被组织成集合(历史记录、采购发票),这为解释它们提供了有用的上下文。为了解决这个问题,我们引入了文档集合视觉问答(DocCVQA),这是一个新的数据集和相关任务,其中问题是针对整个文档图像集合提出的,目标不仅是提供给定问题的答案,还要检索包含推断答案所需信息的文档集合。伴随该数据集,我们提出了一种新的评估指标和基线,为新数据集和任务提供了进一步的见解。

英文摘要:

Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their interpretation. To address this problem, we introduce Document Collection Visual Question Answering (DocCVQA) a new dataset and related task, where questions are posed over a whole collection of document images and the goal is not only to provide the answer to the given question, but also to retrieve the set of documents that contain the information needed to infer the answer. Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑