Google’s new AI tool helps sort through coronavirus research

1
311
Google is adding a helpful new addition to its Images search tool.

Artificial intelligence (AI) continues to makes itself more useful in the field of medicine. Throughout the coronavirus pandemic, it has been more helpful than ever. As the body of research surrounding the virus continues to grow, sorting through it becomes more difficult.

That’s where a new AI-powered tool from Google comes in. It aims to make uncovering relevant COVID-19 information easier for researchers and practitioners. Dubbed the COVID-19 Research Explorer, the search tool lets users query databases with natural language questions rather than complex Boolean terms.

Easier Research Queries

Keith Hall, a Google research scientist, explained how the new tool works in a blog post on Monday. He writes, “Searching through the existing corpus of COVID-19 scientific literature with traditional keyword-based approaches can make it difficult to pinpoint relevant evidence for complex queries.”

Advertisement
Manage your supply chain from home with Sourcengine

Anyone who has used a scholarly database knows that it is completely different than performing a Google search. Typical databases rely on keywords and search modifiers that make it difficult to find information without the perfect search. By contrast, Google uses AI to return information based on a natural language question.

Right now, scientists around the globe are relying on the COVID-19 Open Research Dataset (CORD-19). It includes more than 50,000 journal articles and pre-publication releases. As countless studies examine the effects of COVID-19 and how it can be cured, this database has become increasingly valuable.

Google’s new tool lets researchers use semantic search, a technology that allows a search engine to understand natural language. It uses neural networks to understand a user’s query, scan through the CORD-19 database, and return relevant results.

Hall writes, “When the user asks an initial question, the tool not only returns a set of papers (like in a traditional search) but also highlights snippets from the paper that are possible answers to the question. The user can review the snippets and quickly make a decision on whether or not that paper is worth further reading.”

Following Up

While making searching simpler is already a helpful feature, that isn’t all the new AI tool can do. It also allows researchers to follow-up their initial query with two more questions. This is extremely helpful as it allows users to keep their progress while also expanding a search with multiple different avenues based on the original results.

Google announced that the COVID-19 Research Explorer is now available to the scientific community for free as an “open alpha.”

It also notes that several usability enhancements will be added to the tool in the coming months. However, it won’t be around forever. Google said that the tool will be available on a short-term basis but didn’t specify a set duration.

At this point, it isn’t clear whether it intends to profit off the tool once the COVID-19 pandemic ends by using it for other databases or if it will simply store it away. The former is more likely as semantic search is a helpful feature for researchers that need to analyze studies on complex topics.

1 COMMENT

LEAVE A REPLY

Please enter your comment!
Please enter your name here