You Are All Set!

You now have access to Semantic Reader Beta features including highlighting and note taking.

Illustration: Semantic Reader example showing how citations can be viewed in context of the rest of the paper.
Semantic Reader

Introducing Semantic Reader

An AI-Powered Augmented Scientific Reading Application

What is Semantic Reader?

Semantic Reader is an augmented reader with the potential to revolutionize scientific reading by making it more accessible and richly contextual.

Studies have uncovered many points of friction that break the flow of comprehension when reading technical papers:

  • Frequently paging back and forth looking for the details of cited papers
  • Challenges recognizing the same work across multiple papers
  • Losing track of reading history and notes
  • Contending with a PDF format that is not well suited to mobile reading or assistive technologies such as screen readers

To create a better reading experience, Semantic Reader uses artificial intelligence to understand a document’s structure and merge it with the Semantic Scholar’s academic corpus, providing detailed information in context via tooltips and other overlays. If you’re logged-in, Semantic Reader integrates with your library and, over time, will incorporate personalized contextual augmentations as well.

Semantic Reader interface showing citation detail cards, Table of Contents, Save to Library button, and Cite button

A Revolutionary Reading Experience

Semantic Reader is now available for most arXiv papers on Semantic Scholar with a growing set of features.

  • Citations Cards that show details of a cited paper in-line where you’re reading, including TLDR summaries
  • Table of Contents to quickly navigate between sections (availability varies)
  • Save to Library to conveniently track your reading list

We are incrementally improving, testing, and rolling out new features in Semantic Reader and expanding coverage to more paper sources.

Subscribe to our Product Spotlight emails for updates!


Personalized In-line Citations

With the volume and variety of citations during literature review, it can be challenging to prioritize which ones to explore. In Semantic Reader, citations within a paper are visually augmented based on their connections to your research activities, such as saved in your library or cited by a paper in your library.

If you have at least one paper in your library, this feature is available on desktop devices for you! For more details, visit our FAQ.

We plan to introduce visual augmentation for additional types of connections in the coming months. Stay tuned!

A simplified illustration of a paper shows in-line citations in various colors. One of the citations has been clicked on to reveal a popover containing the text "Cited by a paper saved to your library" and the paper's metadata below that message.
A screenshot shows a PDF reader. Colored labels in the margin that say “Method, Result, or Goal.” Passage of text highlighted in colors corresponding with the labels. A sidebar on the right side of the page which contains the title “Skimming Highlights,” the description “AI-generated highlighting to support skimming,” a Settings button, and a list of extracted text with corresponding labels.


Skim Papers Faster

Find key points of a paper using AI-generated highlighted overlays with 3 category labels: Goal, Method, and Result. Customize the number of highlights and the opacity of highlights from the side panel to create your own experience.

Now available on most English-language arXiv papers in computer science fields.

Illustration: Beta Program

Open Resources for the Community

Create innovative research tools with resources and demos on the Semantic Reader Open Research Platform.

Access open-source libraries for PaperMage and PaperCraft to build intelligent and interactive paper readers. Discover interactive prototype demos developed with these tools.

Explore the Semantic Reader Open Research Platform
A paper with the term "alt text" highlighted. Below the highlighted text, a popover shows text reading "Alt Text: A descriptive text that is added to an image or other visual element on a webpage, providing a textual alternative for individuals who are unable to see or access the visual content." In separate grey text below the definition there is a note that says "AI-Generated Using This Paper"

Definitions On-Demand

Learn definitions for words and acronyms without losing your place in the paper.

Simply click any term with a dotted underline and get an AI-generated definition based on its context in the paper.

For more instructions on using this feature in Semantic Reader, visit our FAQ.

Powered by State-of-the-Art Research

Semantic Reader is based on research from the Semantic Scholar team at AI2, UC Berkeley and the University of Washington, and supported in part by the Alfred P. Sloan Foundation.

Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols
  • September 2020
  • CHI

TLDRThis work introduces ScholarPhi, an augmented reading interface with four novel features: tooltips that surface position-sensitive definitions from elsewhere in a paper, a filter over the paper that “declutters” it to reveal how the term or symbol is used across the paper, automatic equation diagrams that expose multiple definitions in parallel, and an automatically generated glossary of important terms and symbols.

CiteRead: Integrating Localized Citation Contexts into Scientific Paper Reading
  • March 2022
  • IUI

TLDRA novel paper reading experience that integrates relevant information about follow-on work directly into a paper, allowing readers to learn about newer papers and see how a paper is discussed by its citing papers in the context of the reference paper.

Scim: Intelligent Faceted Highlights for Interactive, Multi-Pass Skimming of Scientific Papers
  • May 2022
  • ArXiv

TLDRScim is presented, an AI-augmented reading interface designed to help researchers skim papers by automatically identifying, classifying, and highlighting salient sentences, organized into rhetorical facets rooted in common information needs.

Experience a smarter way to search and discover scholarly research.

Create Your Account

Latest News & Updates

Case Study: Iterative Design for Skimming Support

Case Study: Iterative Design for Skimming Support

How might we help researchers quickly assess the relevance of scientific literature? Take a closer look at Skimming, Semantic Reader’s latest AI feature, and the collaborative design process behind it.

Behind the Scenes of Semantic Scholar’s New Author Influence Design

Behind the Scenes of Semantic Scholar’s New Author Influence Design

We released a new version of Author Influence interface to help scholars better discover other scholars in their fields. Here's how we identified user insights and made those design choices.

Artificial-intelligence search engines wrangle academic literature

Artificial-intelligence search engines wrangle academic literature

Nature had a chat with Dan Weld, Chief Scientist at Semantic Scholar, to discuss how search engines are helping scientists explore and innovate by making it easier to draw connections from a massive collection of scientific literature.