V-Doc : Visual questions answers with Documents
This provides an extensible platform for document visual QA tasks, but appears incremental as it combines existing QA approaches into a unified tool.
The authors tackled the problem of visual question answering on document images and PDFs by developing V-Doc, a tool that supports both extractive and abstractive QA methods for researchers and non-experts, though no concrete performance numbers are provided.
We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks. The V-Doc supports generating and using both extractive and abstractive question-answer pairs using documents images. The extractive QA selects a subset of tokens or phrases from the document contents to predict the answers, while the abstractive QA recognises the language in the content and generates the answer based on the trained model. Both aspects are crucial to understanding the documents, especially in an image format. We include a detailed scenario of question generation for the abstractive QA task. V-Doc supports a wide range of datasets and models, and is highly extensible through a declarative, framework-agnostic platform.