<div dir="ltr"><div class="gmail_default" style="color:#000000">FYI</div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">---------- Forwarded message ---------<br>From: <strong class="gmail_sendername" dir="auto">Peya Mowar</strong> <span dir="auto"><<a href="mailto:pmowar@andrew.cmu.edu">pmowar@andrew.cmu.edu</a>></span><br>Date: Mon, Jul 7, 2025 at 9:46 AM<br>Subject: [MSR Thesis Talk] Towards Automating Accessibility in Digital Authoring Workflows<br>To: RI People <<a href="mailto:ri-people@andrew.cmu.edu">ri-people@andrew.cmu.edu</a>><br></div><br><br><div dir="ltr"><div dir="ltr"><div dir="ltr">Hello everyone,<br>I will be giving my MSR thesis talk on Monday, July 14, 2025 at 12:30 PM EDT in GHC 4405. <div>Everyone is invited!<br><br><b>Date</b>: Monday, July 14th, 2025<br><b>Time</b>: 12:30 PM - 2:00 PM EDT<br><b>Location</b>: Gates and Hillman Center (GHC) 4405<br><b>Zoom Link</b>:<span> </span><a href="https://cmu.zoom.us/j/96220059411?pwd=tLkMb3riHbalo9vwWGVKIZG0A6mnMa.1" target="_blank">https://cmu.zoom.us/j/96220059411?pwd=tLkMb3riHbalo9vwWGVKIZG0A6mnMa.1</a><br><br><b>Title</b>: Towards Automating Accessibility in Digital Authoring Workflows<br><br><b>Abstract</b>:<span> </span><br>Most digital content today remains inaccessible to people with disabilities, who make up 16% of the global population. A long-standing challenge in accessible computing is ensuring digital authors consistently provide the metadata required to make their content accessible through assistive technologies. Despite numerous specialized accessibility tools, authors often lack the time, training, or incentive to use them effectively.<br><br>Recent advancements in AI bring an unprecedented opportunity for automating the production and preservation of accessibility metadata in the authoring process. This thesis argues that developers and content creators can use AI tools to make their digital content accessible with minimal disruption to their existing workflows. It presents two novel AI authoring tools aimed at improving the digital accessibility of websites and scientific documents.<span> </span><br><br>The first, CodeA11y, is an AI coding assistant that helps front-end developers produce accessibility-compliant user interface code. The second, WYISWYM tagging, preserves semantic metadata already present in authored source documents to generate tags and preserve reading order in PDFs. Through comprehensive evaluations, this thesis demonstrates the effectiveness of these tools and represents a first step toward automating accessibility in mainstream digital authoring workflows.</div><div><br><b>Committee</b>:<br>Prof. Jeffrey P. Bigham (advisor)<div>Prof. Aaron Steinfeld (advisor)</div><div>Prof. Deva Ramanan<br>Vivian Shen</div><div><br>--</div><div>Peya Mowar<br>MSR Student, Robotics Institute - CMU<br></div></div><div><a href="http://cs.cmu.edu/~peyajm29" target="_blank">cs.cmu.edu/~peyajm29</a></div></div>
</div>
</div>
</div></div>