A Literature Database with Smarts

Semantic Scholar uses machine reading and vision to extract meaning and impact from academic papers.

Nov 3, 2015
Kerry Grens

PIXABAY, GERALTA new literature search engine called Semantic Scholar aims to help researchers not just find relevant papers but make sense of their content and impact as well. The Allen Institute for Artificial Intelligence launched the database this week (November 2).

“We want ultimately to be able to take an experimental paper and say, ‘Okay, do I have to read this paper, or can the computer tell me that this paper showed that this particular drug was highly efficacious?’” Oren Etzioni, executive director of the institute, told MIT Technology Review.

Google Scholar, PubMed, and a handful of other databases are currently the go-to source to search the academic literature. But their analytical abilities are limited.

“Google has access to a lot of data. But there’s still a step forward that needs to be taken in understanding the content of the paper,” Jose Manuel Gomez-Perez, the director of research and development for the software company Expert System, told Nature.

Semantic Scholar will help users make sense of those papers. For instance, the search engine will provide information on how often a paper’s references have been cited and it will display graphical results.

“Which papers are most relevant? Which are considered the highest quality? Is anyone else working on this specific or related problem?” Etzioni asked in a press release. “Now, researchers can begin to answer these questions in seconds, speeding research and solving big problems faster.”