From the UC Berkeley School of Information:
The project is led by UC Berkeley School of Information Professor Marti Hearst, and includes UC Berkeley postdoctoral fellows Andrew Head and Dongyeop Kang, and collaborators Raymond Folk, Kyle Lo, Sam Sjonsberg, and Dan Weld from the Allen Institute for AI (AI2) and the University of Washington. It is funded in part by the Alfred P. Sloan Foundation and by AI2.
ScholarPhi broadens access to scientific literature by developing a new document reader user interface and natural language analysis algorithms for context-relevant explanations of technical terms and notation.
“The goal of this project is to help democratize understanding of complex scientific literature,” said Professor Hearst. “The AI literature is a case study; the papers are often technically dense. This is our take on explainable AI.”
While the interface has only been evaluated in the lab with manually-edited definitions, the team is working to advance the state-of-the-art in automated definition recognition. The team is also working closely with the team at AI2 that develops the Semantic Scholar academic search engine to release an interactive reading application that will eventually make the reading experience available for millions of papers.
The ScholarPhi project appears as a full paper at the ACM CHI Conference on Human Factors in Computing Systems, a premier conference in human-computer interaction, the week of May 10, 2021. To learn more about the project, watch the video presentation for the CHI paper, or try out the online demo of the user interface.
Read the Complete Summary Article
Direct to ScholarPhi