19 July, 2017

Google scientist teaches how to cure yourself using the almighty search engine

Senior research scientist Dr. Evgeniy Gabrilovich paid a visit to the HKUST Big Data Institute (BDI) in the mid-summer on 19 July 2017 to meet with BDI faculty and to give a talk titled “Cura Te Ipsum: Health Search at Google”. The title borrows the Latin phase Cura Te Ipsum (literally means “you cure yourself”), a proverb found as early as in Bible (Luke 4:23) where Jesus quoted in Greek as “Physician, heal thyself”.

Approximately one percent of all Google searches are symptom-related, as users are conducting online research on pertinent medical conditions. In this talk, he discussed the recently launched symptom search experience on Google. He shared that Google use machine learning methods to identify queries with condition-seeking intent, they then extract relevant health conditions by analyzing the web search results as well as by consulting the Knowledge Graph, and finally, they learn a ranker for ordering the list of relevant conditions, and evaluate the system performance with medical doctors. He also shared the difficulties faced in developing the symptom search mechanism, how the Google team keeps improving, and the way forward for further development in the enhancement of helpfulness and user experience.

The talk was well received with loads of questions asked by participants exploring a better way forward for the service that is likely applicable to everyone searching on Google. Currently this new launch is already seen in the US and Brazil, with possibly expanding potential, when localization and other technical difficulties can be overcome in time.

Dr. Evgeniy Gabrilovich is a senior staff research scientist at Google, where he works on improving healthcare. Prior to joining Google in 2012, he was a director of research and head of the natural language processing and information retrieval group at Yahoo! Research. Evgeniy is an ACM Distinguished Scientist, and is a recipient of the 2014 IJCAI-JAIR Best Paper Prize. He is also a recipient of the 2010 Karen Sparck Jones Award for his contributions to natural language processing and information retrieval. Evgeniy has served as a program chair for WWW 2017 and WSDM 2015. He earned his PhD in computer science from the Technion - Israel Institute of Technology. Recently, he graduated (with extra credit) from the Executive MD training program at Harvard Medical School.