A free tool for uncovering supplement-drug interactions: supp.ai | Powered by Semantic Scholar

Cut through the clutter.

Home in on key papers, citations, and results.

Leverage AI To Combat Information Overload

With millions of research papers published every year, there is a huge information overload in scientific literature search. Semantic Scholar leverages our AI expertise to help researchers find the most relevant information efficiently. We utilize methods from data mining, natural-language processing, and computer vision to create powerful new search and discovery experiences. Starting with Computer Science in 2015, we've since scaled the service to all fields of science and are now investing heavily in value-add features in support of AI2’s mission of "AI for the Common Good."

Projects Currently Under Development
  • Addition of relevant scientific content that supplement and summarize research papers and concepts.
  • Innovation in search and discovery with a focus on filters and smarter search capabilities.
  • Extraction of key metadata from papers to generate useful research summaries.
  • Identification and presentation of useful concepts and their relationships.
  • Customizable research tools that empower researchers to reach their objectives.

Open Source Tools

Public API & Open Research Corpus

Semantic Scholar makes data about research papers in our corpus freely available through a public API and in bulk through our open research corpus.

APIOpen Corpus

Cite-o-matic: Automated Literature Review

Cite-o-matic is a deep learning model for literature review, specifically trained to learn to give meaningful predictions, even when it’s wrong. Cite-o-matic requires only a title and abstract to give useful results, allowing it to be used at any stage in the writing process.


Science Parse: PDF Metadata Extraction

This state-of-the-art tool extracts relevant metadata from PDFs of scholarly articles, including titles, author information, abstracts, sections and references.

Repo V1Repo V2

DeepFigures: PDF Image and Caption Extractor

The DeepFigures project uses deep learning to extract both image- and text-based figures from academic PDFs with high precision and recall.


How Semantic Scholar Works

PDF Extraction

State of the art PDF extraction mechanisms specifically targeted to scholarly articles.

Targeted Search Index

For serving relevant results for queries specific to the academic domain.

Customized GUI

A user interface tailored to academic search with features that support the academic community.

“Impossible is not a fact. It’s an opinion.”
—  Muhammad Ali

Other Projects

  • AllenNLP

    Deep Semantic NLP Platform

    Learn More
  • Aristo

    Answering science questions

    Learn More

    Perceptual Reasoning and Interaction Research

    Learn More