The goal of the ScholarPhi project was to improve the reading of scientific papers by helping readers see the meanings of mathematical symbols, technical terms, and other information directly where they are used within the paper.

The ScholarPhi project was led by researchers from UC Berkeley, the Allen Institute for AI (AI2), and the University of Washington. The project was supported by AI2 and the Alfred P. Sloan Foundation.

Demo, Software, and Impact

ScholarPhi research results have had real world impact.

ScholarPhi Publications

Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols

Andrew Head, Kyle Lo, Dongyeop Kang, Raymond Fok, Sam Skjonsberg, Daniel S. Weld, and Marti A. Hearst

ACM CHI Conference on Human Factors in Computing Systems 2021

Math Augmentation: How Authors Enhance the Readability of Formulas using Novel Visual Design Practices

Andrew Head, Amber Xie, and Marti A. Hearst

ACM CHI Conference on Human Factors in Computing Systems 2022

Document-Level Definition Detection in Scholarly Documents: Existing Models, Error Analyses, and Future Directions

Dongyeop Kang, Andrew Head, Risham Sidhu, Kyle Lo, Daniel S. Weld, and Marti A. Hearst

EMNLP First Workshop on Scholarly Document Processing 2020

PDF

Modeling Mathematical Notation Semantics in Academic Papers

Hwiyeol Jo, Dongyeop Kang, Andrew Head, and Marti A. Hearst

Findings of EMNLP 2021

Publications that Make Use of the ScholarPhi Reader

CiteRead: Integrating Localized Citation Contexts into Scientific Paper Reading

Napol Rachatasumrit, Jonathan Bragg, Amy X. Zhang, Daniel S. Weld

ACM Conference on Intelligent User Interfaces 2022

Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing

Tal August, Lucy L. Wang, Jonathan Bragg, Marti A. Hearst, Andrew Head, Kyle Lo

arXiv pre-print 2203.00130 (2022)

Scim: Intelligent Faceted Highlights for Interactive, Multi-Pass Skimming of Scientific Papers

Raymond Fok, Andrew Head, Jonathan Bragg, Kyle Lo, Marti A. Hearst, and Daniel S. Weld

arXiv pre-print 2205.04561 (2022)

Core Team

Marti A. Hearst
Professor, UC Berkeley
Daniel S. Weld
Professor, UW, Senior Research Manager, AI2
Sam Skjonsberg
Principal software engineer, AI2
Kyle Lo
Applied research scientist, AI2
Raymond Fok
Ph.D. student, UW
Dongyeop Kang
Postdoctoral scholar,
UC Berkeley, now Assistant Professor at U Minnesota
Andrew Head
Postdoctoral scholar,
UC Berkeley, now Assistant Professor at U Pennsylvania