VisText: Teaching AI to Write Better Accessible Chart Captions
VisText: A Benchmark for Semantically Rich Chart Captioning
Published: 2023-07-02
Author: Massachusetts Institute of Technology | Contact: web.mit.edu
Peer-Reviewed: N/A | Publication Type: Reports and Proceedings
Journal Reference: DOI Link to the Study Paper
Related Papers: Latest Items | Complete List
On This Page: Summary | Defining VisText | Main Article | About/Author
Synopsis: New dataset can help scientists develop automatic systems that generate richer, more descriptive online chart captions for people with disabilities. For people with visual disabilities, the information in a caption often provides their only means of understanding the chart. Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such captions struggle to articulate the perceptual or cognitive features that are the hallmark of charts (e.g., complex trends and patterns).
sponsored links
Definition
VisText
VisText is a benchmark dataset of over 12,441 charts and semantically rich captions! In the VisText dataset, each chart is represented as its rasterized image, scene graph specification, and underlying datatable. Each chart is paired with a synthetic L1 caption that describes the chart’s elemental and [...]