The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces

• DOI: 10.48550/arxiv.2303.14334
• Publication Date: 2023-01-01
• Authors: Kyle Lo; Joseph Chee Chang; Andrew Head; Jonathan Bragg; Amy X. Zhang; Cassidy Trier; Chloe Anastasiades; Tal August; Russell Authur; Danielle Bragg; Erin Bransom; Isabel Cachola; Stefan Candra; Yoganand Chandras...; Yen-Sung Chen; Evie Yu-Yen Cheng; Yvonne Chou; Doug Downey; R. L. Evans; Raymond Fok; Fangzhou Hu; Regan Huff; Dongyeop Kang; Tae Soo Kim; Rodney Kinney; Aniket Kittur; Hyeonsu B Kang; Egor Klevak; Bailey Kuehl; Michael Langan; Matt Latzke; Jaron Lochner; Kelsey MacMillan; Eric D. Marsh; Tyler Murray; Aakanksha Naik; Ngoc-Uyen Nguyen; Srishti Palani; Soya Park; Caroline Paulic; Napol Rachatasumrit; Smita Rao; Paul L Sayre; Zejiang Shen; Pao Siangliulue; Luca Soldaini; Huy Tran; Madeleine van Zuylen; Lucy Lu Wang; Christopher Wilhelm; Caroline Wu; Jiangjiang Yang; Angele Zamarron; Marti A. Hearst; Daniel S. Weld
• Keywords: Software portability

Scholarly publications are key to the transfer of knowledge from scholars others. However, research papers information-dense, and as volume scientific literature grows, need for new technology support reading process grows. In contrast finding papers, which has been transformed by Internet technology, experience changed little in decades. The PDF format sharing is widely used due its portability, but it significant downsides including: static content, poor accessibility low-vision readers, difficulty on mobile devices. This paper explores question "Can recent advances AI HCI power intelligent, interactive, accessible interfaces -- even legacy PDFs?" We describe Semantic Reader Project, a collaborative effort across multiple institutions explore automatic creation dynamic papers. Through this project, we've developed ten prototype conducted usability studies with more than 300 participants real-world users showing improved experiences scholars. We've also released production interface that will incorporate best features they mature. structure around challenges public face when Discovery, Efficiency, Comprehension, Synthesis, Accessibility present an overview our progress remaining open challenges.