Document Visual Question Answering (DocVQA) refers to the task of answering
questions from document images. Existing work on DocVQA only considers
single-page documents. However, in real scenarios documents are mostly composed
of multiple pages that should be processed altogether. In this work we extend
DocVQA to the multi-page scenario. For that, we first create a new dataset,
MP-DocVQA, where questions are posed over multi-page documents instead of
single pages. Second, we propose a new hierarchical method, Hi-VT5, based on
the T5 architecture, that overcomes the limitations of current methods to
process long multi-page documents. The proposed method is based on a
hierarchical transformer architecture where the encoder summarizes the most
relevant information of every page and then, the decoder takes this summarized
information to generate the final answer. Through extensive experimentation, we
demonstrate that our method is able, in a single stage, to answer the questions
and provide the page that contains the relevant information to find the answer,
which can be used as a kind of explainability measure.

本研究扩展了针对单页文档的 DocVQA 任务到多页文档的场景，提出了一个基于 T5 架构的新的分层方法 Hi-VT5，用于处理长的多页文档，并且通过实验证明本方法可以在单阶段完成回答问题和提供包含答案相关信息的页码，该信息可以作为可解释性量度。