DVQA: Understanding Data Visualizations via Question Answering
This work addresses the challenge of automatically extracting information from bar charts in various domains like scientific publications and business reports, though it is incremental as it builds on VQA with a new dataset and baselines.
The authors tackled the problem of algorithms failing to understand bar charts with minor appearance variations by introducing DVQA, a dataset for bar chart question answering, and proposed two baselines that significantly outperformed existing VQA methods.
Bar charts are an effective way to convey numeric information, but today's algorithms cannot parse them. Existing methods fail when faced with even minor variations in appearance. Here, we present DVQA, a dataset that tests many aspects of bar chart understanding in a question answering framework. Unlike visual question answering (VQA), DVQA requires processing words and answers that are unique to a particular bar chart. State-of-the-art VQA algorithms perform poorly on DVQA, and we propose two strong baselines that perform considerably better. Our work will enable algorithms to automatically extract numeric and semantic information from vast quantities of bar charts found in scientific publications, Internet articles, business reports, and many other areas.