Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols
Andrew Head (UC Berkeley), Kyle Lo (Allen Institute for AI), Dongyeop, Kang (UC Berkeley), Raymond Fok (University of Washington), Sam Skjonsberg, (Allen Institute for AI), Daniel S. Weld (Allen Institute for AI, University, of Washington), Marti A. Hearst (UC Berkeley)

TL;DR
ScholarPhi enhances scientific paper reading by providing just-in-time, position-sensitive definitions, decluttering tools, and automatic glossaries, thereby improving comprehension for researchers of all levels.
Contribution
This work introduces ScholarPhi, a novel interface with four features that deliver context-aware definitions and visualization tools to improve scientific paper comprehension.
Findings
Researchers found ScholarPhi improved understanding of complex terms.
The tool was useful across different experience levels.
Researchers expressed strong interest in integrating ScholarPhi into their workflow.
Abstract
Despite the central importance of research papers to scientific progress, they can be difficult to read. Comprehension is often stymied when the information needed to understand a passage resides somewhere else: in another section, or in another paper. In this work, we envision how interfaces can bring definitions of technical terms and symbols to readers when and where they need them most. We introduce ScholarPhi, an augmented reading interface with four novel features: (1) tooltips that surface position-sensitive definitions from elsewhere in a paper, (2) a filter over the paper that "declutters" it to reveal how the term or symbol is used across the paper, (3) automatic equation diagrams that expose multiple definitions in parallel, and (4) an automatically generated glossary of important terms and symbols. A usability study showed that the tool helps researchers of all experience…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
