Depending on who you ask, AI can be fascinating, terrifying or some combination of the two. But Adobe’s accessibility-focused artificial intelligence is a use case that (I hope) any reasonable person can get behind. The company’s new Auto-Tag API takes the tedium out of creating accessibility-friendly PDFs for people with disabilities.
PDFs have built-in metadata that provides structural information – headings, paragraphs, lists and tables – in documents for assistive tech such as screen readers. But tagging digital documents for compatibility can be time-consuming, especially for those with complex layouts or companies with backlogs of old files that lack the right metadata. Adobe estimates that more than 90 percent of PDFs are at least not accessible to people with disabilities, sometimes “appearing blank, blurred or as lines of distorted text.”
Adobe’s PDF Accessibility Auto-Tag API automates the tagging process. The company says its Sensei-powered software will show the correct reading order for the technology to help, save companies time and – more to the point – make PDFs more readable. for people with disabilities. Adobe says the AI can easily wade through stockpiles of old documents that lack proper structure.
The company also launched a PDF Accessibility Checker, which “enables organizations to quickly and easily evaluate the accessibility of existing PDFs at scale.”
In addition to the developer-facing API, Auto-Tag is coming to Acrobat Pro in June, offering automatic structuring of metadata within the app at no additional cost for all subscribers. The feature is also coming to Acrobat Reader this fall.