A new search engine for scientists was launched by the Allen Institute for Artificial Intelligence (AI2 ) giving researchers more powerful tools to search through the millions of academic papers available online.

The free product is called Semantic Scholar and is able to search about 3 million open-access papers in computer science. “We’re trying to get deep into the papers and be fast and clean and usable,” says Oren Etzioni, chief executive officer of AI2 aiming to broaden the search to other fields within a year.

AI2 was founded and is backed by Microsoft co-founder Paul Allen, who has given the institute more than US$20 million since 2013.

Semantic Scholar offers innovative features, such as picking out the most important keywords and phrases from the text without relying on an author or publisher to key them in.

It can also identify which of a paper’s cited references were truly influential, rather than being included incidentally for background or as a comparison.