AI cuts huge research papers down to one sentence

Semantic Scholar is an AI-powered tool used for scientific research. Thanks to the new

abstracting function it scans a huge number of research papers and condenses them into one sentence. 

Currently there are more than 10 in the Semantic Scholar databasemillion articles on computer science. Articles from other disciplines will gradually be added, according to Dan Weld, an information scientist at the University of Washington in Seattle who oversees the database.

The system helps researchers who are stillSince then, they have had to rely on scanning numerous headlines and often lengthy abstracts, which is particularly challenging on mobile devices. After the first tests of the system, the reaction of users was positive.

Semantic Scholar has the highestcompression ratio among all tools. Science articles average 5,000 words, but the AI ​​tool shortens them to 21 words. The closest competitor, Semantic Scholar, compresses documents 36 times, and the new system - 238 times.

The Allen Institute team makes its code available for free. They have also created a demo site that is available to everyone.

So far, only works written in English are accepted. But the authors of the program hope to eventually include documents in other languages.

Read also

Found the alleged kingdom of the disappeared Hittites. What have archaeologists found?

Scientists have studied how COVID-19 is transmitted indoors

From January 1, all smartphones must have 16 Russian applications