Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, Kosuke Nishida, Ryota Tanaka, Itsumi Saito
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Visual question answering on document images that contain textual, visual, and layout information, called document VQA, has received much attention recently. Although many datasets have been proposed for developing document VQA systems, most of the existing datasets focus on understanding the content relationships within a single image and not across multiple images. In this study, we propose a new multiimage document VQA dataset, SlideVQA, containing 2.6k+ slide decks composed of 52k+ slide images and 14.5k questions about a slide deck. SlideVQA requires complex reasoning, including single-hop, multi-hop, and numerical reasoning, and also provides annotated arithmetic expressions of numerical answers for enhancing the ability of numerical reasoning. Moreover, we developed a new end-to-end document VQA model that treats evidence selection and question answering in a unified sequence-to-sequence format. Experiments on SlideVQA show that our model outperformed existing state-of-the-art QA models, but that it still has a large gap behind human performance. We believe that our dataset will facilitate research on document VQA.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2301.04883")
get_code_for_paper("2301.04883")
have("2301.04883")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2301.04883.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2301.04883)
Connect an agent — have() is free.