Scientific papers come out with such frequency that keeping up with the literature is practically a full-time job for anyone at the cutting edge of a major field.

Semantic Scholar, a free, online tool developed under the guidance of Microsoft cofounder Paul Allen, is using machine learning and other aspects of artificial intelligence (AI) to make the monumental task of parsing the scientific literature less onerous.

Semantic Scholar analyzes the full text of the article, looking for key phrases that it knows, from reading a hundred thousand other articles in the field, are important to track. It uses natural language processing so it understands when a paper is discussing its own results or those of another experiment, and from there can extract critical details like methods, materials, animal types or brain regions tested, etc. It pulls figures when it can, attempting to identify the contents so they too can be searched and sorted.

semantic search engine AI

The main benefit of Semantic Scholar, which its creators say will soon be expanded to include the full biomedical literature, is that the AI-driven engine is able to understand the content and context of scientific papers, searching figures within an article, for example, rather than just listing its abstract and raw bibliographic data.

But early reports suggest that Semantic Scholar isn’t yet 100 percent debugged. “Looking at ‘most influential publications’ sometimes gives strange results,” Sam Gershman, a Harvard University computational neuroscientist told ScienceInsider. “For example, none of the most influential articles listed for [University of California, Berkeley, psychologist] Thomas Griffiths fall into his top five most cited articles.”

You can test out Semantic Scholar right now, though if you’re not in CS or neuroscience you may not find many results to your liking.