Hit enter to search or ESC to close

About Paper Digest

About Us

We are a New York based research group working on text analysis. We were founded in 2018 by Dr. Chang Wang. Our mission is to produce high quality text analysis results that people can actually use on a daily basis. We also maintain one of the largest sci-tech knowledge graphs in the world. Different from other knowledge graphs, we are able to connect research and development activities to business activities and financial activities.
Currently, we offer the following services related to scientific literature analysis:

      • Daily paper digest (introduced in early 2018)
        • subscribers receive customized daily updates on papers published on previous day;
      • Conference paper digest (introduced in mid 2019)
        • one-sentence highlight for every paper published in a conference;
      • Paper/Patent/Grant/Expert search (introduced in early 2020)
        • search results are associated with “related” features and one-sentence highlight
      • Real-time topic tracking (introduced in early 2020)
        • including paper tracking, patent tracking and grant tracking;
      • “Best paper” digest (introduced in early 2021)
        • present 10 most influential papers for each conference / journal & year;

We track and analyze all new papers uploaded to major academic paper websites (like arxiv, biorxiv, pubmed, medrxiv) as well as thousands of conferences and journals. We also track other technology related data like  patents (>10M) and government grants (>3M). Our finance, business activity and organization related data is provided by FMeasure. Our person related data is provided by Expert Graph.

A fairly complicated text analysis platform has been built to support our services. The platform contains:

  • a central knowledge graph storing hundreds of millions of documents;
  • several search components providing paper, patent, grant and expert search results;
  • a number of site crawlers tracking new papers and other related documents in real-time;
  • a pipeline with dozens of built-in natural language processing and machine learning components to analyze documents. For example, we have more than 5 different algorithms that can be applied to generate highlights from research papers: from rule-based to transformer-based.


Our users come from more than 100 countries across the world. Most of them are researchers, engineers, professors and graduate students. Some business men, reporters and investors also use our services to track trending topics and the most recent research progresses.

  • team@paperdigest.org
  • 12 E 49th St, 9th Floor, New York, NY, USA, 10017