The Semantic Reader Project
Scholarly publications are key to the transfer of knowledge from scholars to others. However, research papers are information-dense, and as the volume of the scientific literature grows, the greater the need for new technology to support scholars. In contrast to the process of finding papers, which has been transformed by Internet technology, the experience of reading research papers has changed little in decades. For instance, the PDF format for sharing papers remains widely used due to its portability but has significant downsides, inter alia, static content and poor accessibility for low-vision readers. This paper explores the question “Can recent advances in AI and HCI power intelligent, interactive, and accessible reading interfaces—even for legacy PDFs?” We describe the Semantic Reader Project, a collaborative effort across multiple institutions to explore automatic creation of dynamic reading interfaces for research papers. Through this project, we’ve developed a collection of novel reading interfaces and evaluated them with study participants and real-world users to show improved reading experiences for scholars. We’ve also released a production research paper reading interface that will continuously incorporate novel features from our research as they mature. We structure this paper around five key opportunities for AI assistance in scholarly reading —discovery, efficiency, comprehension, synthesis, and accessibility—and present an overview of our progress and discuss remaining open challenges.
Authors
- Evie Yu-Yen Cheng (ORCID: https://orcid.org/0009-0002-6054-1688)
- Lucy Lu Wang (ORCID: https://orcid.org/0000-0001-8752-6635)
- Yoganand Chandrasekhar
- Andrew J. Head (ORCID: https://orcid.org/0000-0002-1523-3347)
- Pao Siangliulue (ORCID: https://orcid.org/0009-0006-8042-885X)
- Napol Rachatasumrit (ORCID: https://orcid.org/0000-0002-7183-8789)
- Rob Evans (ORCID: https://orcid.org/0009-0001-4549-2083)
- Marti A. Hearst (ORCID: https://orcid.org/0000-0002-4346-1603)
- Srishti Palani (ORCID: https://orcid.org/0000-0003-1805-7307)
- Caroline Paulic (ORCID: https://orcid.org/0009-0005-2237-5262)
- Angele Zamarron (ORCID: https://orcid.org/0009-0009-2130-5309)
- Egor Klevak (ORCID: https://orcid.org/0000-0002-0874-0578)
- Hyeonsu B Kang (ORCID: https://orcid.org/0000-0002-1990-2050)
- Tyler Murray (ORCID: https://orcid.org/0000-0003-0043-7192)
- Tal August (ORCID: https://orcid.org/0000-0001-6726-4009)
- Erin Bransom (ORCID: https://orcid.org/0009-0006-2212-2959)
- Bailey Kuehl
- Amy Xian Zhang (ORCID: https://orcid.org/0000-0001-9462-9835)
- Jonathan Bragg (ORCID: https://orcid.org/0000-0001-5460-9047)
- Cassidy Trier (ORCID: https://orcid.org/0000-0001-6317-6968)
- Zejiang Shen
- Dongyeop Kang (ORCID: https://orcid.org/0000-0002-9021-1789)
- Danielle Bragg (ORCID: https://orcid.org/0000-0002-7846-3481)
- Doug Downey (ORCID: https://orcid.org/0000-0002-4737-8444)
- Matt Latzke (ORCID: https://orcid.org/0000-0002-9984-1277)
- Chloe Anastasiades (ORCID: https://orcid.org/0009-0009-5595-2299)
- Aniket Kittur (ORCID: https://orcid.org/0000-0003-4192-9302)
- S. A. RAO
- Isabel Cachola (ORCID: https://orcid.org/0000-0002-8682-0223)
- Rodney Kinney (ORCID: https://orcid.org/0000-0002-3582-6537)
- Luca Soldaini (ORCID: https://orcid.org/0000-0001-6998-9863)
- Stefan Candra
- Regan Huff
- Raymond Fok (ORCID: https://orcid.org/0000-0002-0612-5782)
- Kyle Lo (ORCID: https://orcid.org/0000-0002-1804-2853)
- Michael Langan (ORCID: https://orcid.org/0009-0006-0702-4891)
- Soya Park (ORCID: https://orcid.org/0000-0002-2149-4420)
- Ngoc-Uyen Nguyen
- Paul L Sayre (ORCID: https://orcid.org/0009-0008-0919-0804)
- Kelsey MacMillan (ORCID: https://orcid.org/0009-0007-4634-1010)
- Yvonne Chou
- Christopher Wilhelm (ORCID: https://orcid.org/0000-0002-9359-1561)
- Russell Authur (ORCID: https://orcid.org/0009-0002-1238-4323)
- Daniel S. Weld (ORCID: https://orcid.org/0000-0002-3255-0109)
- Aakanksha Naik (ORCID: https://orcid.org/0000-0002-3673-0051)
- Yen-Sung Chen (ORCID: https://orcid.org/0009-0005-4660-682X)
- Jaron Lochner (ORCID: https://orcid.org/0009-0009-1402-092X)
- Caroline Wu (ORCID: https://orcid.org/0009-0001-1099-5529)
- Fangzhou Hu (ORCID: https://orcid.org/0009-0007-8589-3643)
- Joseph Chee Chang (ORCID: https://orcid.org/0000-0002-0798-4351)
- Zuylen Madeleinevan (ORCID: https://orcid.org/0000-0003-3062-2938)
- Huy Tran
- Eric Marsh
- SooKim Tae
- Jiangjiang Yang
Institutions
- Northwestern University (US)
- Microsoft (United States) (US)
- Johns Hopkins University (US)
- Emory University (US)
- Korea Advanced Institute of Science and Technology (KR)
- University of Washington (US)
- University of Minnesota System (US)
- University of California San Diego (US)
- Allen Institute for Artificial Intelligence (US)
- Massachusetts Institute of Technology (US)
- Carnegie Mellon University (US)
- University of Pennsylvania (US)
- University of California, Berkeley (US)
Publication Details
- Journal
- Communications of the ACM
- Published
- 2024-09-19
- DOI
- https://doi.org/10.1145/3659096
- Citations
- 10
- Primary Topic
- Digital Humanities and Scholarship
- Type
- article
- Field-Weighted Citation Impact
- 39.08
Funders
- National Science Foundation
- Office of Naval Research