- Kyle Chua
Adobe’s AI-Powered Auto-Tag API Automates PDF Making Processes
Updated: Dec 19, 2023
Adobe is leveraging artificial intelligence (AI) technology to make PDFs more accessible to individuals with disabilities ahead of Global Accessibility Awareness Day.
The software giant announced the Adobe PDF Accessibility Auto-Tag API, a new tool that automates and streamlines the process of making digital documents more accessible, saving organisations time and money, while improving the employee and customer experience. The API is powered by Adobe Sensei, the company's AI and machine learning framework.
"From complex legal agreements and contracts to mortgage documents and school permission slips – making digital documents accessible to as many people as possible is both the right thing to do as well as a legal and business imperative for companies that want to compete globally," said Todd Gerber, VP of Product Marketing at Adobe Document Cloud.
Adobe says as much as 90% of the trillions of PDF documents in circulation today are at least partially inaccessible for individuals with disabilities as they could appear blank, blurry or as lines of distorted text. That is likely due to how time-consuming and difficult it is to manually make these documents accessible, requiring extensive training and expertise. Adobe's new API is changing that, with early adopters said to be automating 70-100% of the process and cutting the time required to make each file fully accessible.
What the API does is it leverages Sensei to automate and scale the process of tagging PDF content structures. It identifies headings, paragraphs, lists and tables in documents, also indicating the correct reading order for assistive technologies like screen readers to make it accessible for those who are dyslexic, blind or have low vision. Developers can apply the API to backlogs of existing PDFs to start resources.
Adobe additionally announced two new features that are coming later in the year. The PDF Accessibility Checker, which is coming to Acrobat via an API, is a new innovation that enables organisations to quickly and easily evaluate the accessibility of existing PDFs at scale. Meanwhile, Auto-Tag in Acrobat Reader gives existing customers a more accessible viewing experience within app for free, without the need for separate plug-ins or downloads.
Adobe also looks to elevate accessibility through community collaboration. The company last year formed the Readability Consortium in partnership with the University of Central Florida, Readability Matters and Google, to help make digital reading and reading comprehension more equitable for all through investments in cognitive research, open-source tools and user tests.
In line with this, Adobe's Document Cloud research team has published two new papers that focuses on the design of alternate digital reading formats and customer interfaces to promote more comfortable and enjoyable individual reading experiences.
Adobe has announced the Adobe PDF Accessibility Auto-Tag API, a new tool that automates and streamlines the process of making digital documents more accessible, saving organisations time and money, while improving the employee and customer experience.
The API is powered by Adobe Sensei, the company's AI and machine learning framework.
What the API does is it tags PDF content structures, and indicates the correct reading order for assistive technologies like screen readers to make it accessible for those who are dyslexic, blind or have low vision.