Research Tools: Semantic Scholar’s New “TLDR” (Beta) Feature Uses NLP to Place “Single-Sentence, Automatically-Generated Paper Summaries” on Search Results Pages

Editors Note: We’re big fans and constant users of the wonderful Semantic Scholar open web database of journal and open access material. It’s free to access and use. As of today Semantic Scholar provides access (full text and/or metadata) to 194 million items. infoDOCKET has been posting and talking about Semantic Scholar since it launched on November 2, 2015.  If you’ve never visited, it’s more than worthy of your attention. Btw, along with searching Semantic Scholar we find their new article alerts timely and useful.

From the TLDR Information Page:

The new TLDR feature in Semantic Scholar puts single-sentence, automatically-generated paper summaries right on the search results page, allowing you to quickly locate the right papers and spend your time reading what matters to you.

TLDRs (Too Long; Didn’t Read) are super-short summaries of the main objective and results of a scientific paper generated using expert background knowledge and the latest GPT-3 style NLP techniques. This new feature is available in beta for nearly 10 million papers and counting in the computer science domain in Semantic Scholar.

[Clip]

TLDRs help users make quick informed decisions about which papers are relevant, and where to invest the time in further reading. TLDRs also provide ready-made paper summaries for explaining the work in various contexts, such as sharing a paper on social media.

Learn More, Read the Complete Introduction

Direct to Semantic Search Search Interface

Filed under: Journal Articles, News, Open Access, Patrons and Users