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.
A Revolutionary Reading Experience
Semantic Reader is now available for most arXiv papers on Semantic Scholar with an introductory 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!
Skim Papers Faster
Find key points of this paper using automatically highlighted overlays. Available in beta on limited papers for desktop devices only.
We're actively seeking feedback for this experimental new feature! Try now and tell us how Skimming can better help you understand papers faster.
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- ALBERT: A Lite BERT For Self-supervised Learning of Language Representations
- Google’s Multilingual Neural Machine Translation System:Enabling Zero-Shot Translation
Try Out Semantic Reader
Here are examples of Semantic Reader operating over popular Computer Science papers across various subfields. The current design is best experienced on a full-size screen.
Natural Language Processing
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
- Long-term Recurrent Convolutional Networks for Visual Recognition and Description
- Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
- Rethinking the Inception Architecture for Computer Vision
Send us your Semantic Reader feedback.
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.