Welcome Google AI COVID-19 Research Explorer

Google launched the COVID-19 Research Explorer, a semantic search interface on top of the COVID-19 Open Research Dataset (CORD-19)

Welcome Google AI COVID-19 Research Explorer
Google AI: New COVID-19 Research Explorer for Scientific Literature

Google AI: New COVID-19 Research Explorer

There are dozens of scientists and medical researchers publishing newly find research data on a public domain to combat the deadly pandemic. The research information volume is in rapid incline, scientists and researchers find it difficult to search for specific data. 

There are traditional search algorithms do the best retrieving data for simple COVID-19 specific question such as "How many COVID-19 cases are there in the United States?". However existing logic was unable to differentiate the meaning specific to complex,  research-driven queries. 

Google launching the COVID-19 Research Explorer, brand new search interface connected to the COVID-19 Open Research Dataset (CORD-19). 

As per google standard blog, the new search interface provides access to more than 50,000 journal articles and pretexts.

Also, google enhanced the tool interface for scientists and researchers to bookmark articles, answers, or evidence to COVID-19-related questions.


New Model 

The tool is intelligent to return with highlights snippets from the paper, and suggested answers for a specific question.  

The tool also facilitates users to review and comment, embedded follow up questions, which act as new queries for the original search keyword. 

The user can review the snippets and quickly make a decision on whether or not that paper is worth further reading. If the user is satisfied with the initial set of papers and snippets, we have added functionality to pose follow-up questions, which act as new queries for the original set of retrieved articles. 
 

Semantic Search

The new tool is powered by technology based on semantic search. Semantic search is able to understand the phrases and meaning relevance and predict the true intent behind the search query.

 


The semantic search technology powered by a company called BERT to improve the quality of Google Search

Google also able to successfully meet the challenges faced as biomedical literature use a totally different language and different queries.

In general Neural semantic search models do require massive amounts of training data, Google deployed advances in query generation to populate the relevant documents in the biomedical domain.

Availability and Future 

THE New COVID-19 Research Explorer tool is freely available. Google is expecting to enhance the tool based on the feedback over usability to improve COVID-19 Research Explorer