Chris Welty
Google Research
Dr. Chris Welty's main area of interest is equal parts machine learning, knowledge bases, and crowdsourcing, and his recently published work is on using crowdsourcing to form a new theory of truth based on diversity of perspectives. He is a firm advocate of data as the compass for AI, and has espoused the view that engineering and acquisition of data are far more important to progress than algorithm development. Before Google, Dr. Welty was a member of the technical leadership team for IBM’s Watson – the question-answering computer that defeated the all-time best Jeopardy! champions in a widely televised contest. Since joining Google in 2014, he has worked on incorporating AI in Google products such as Google Docs and Maps. He got his start 30 years ago working summers at AT&T Bell Labs under Ron Brachman on Knowledge Representation, and became known for OntoClean, the first formal methodology for evaluating ontologies. He is on the editorial board of AI Magazine, where he curates the "AI Bookie", a column that focuses on scientific bets for AI. Dr. Welty holds a Ph.D. in Computer Science from Rensselaer Polytechnic Institute (RPI).

2021 Talk: Shopping Sense: Bringing common sense to worldwide shopping knowledge

Knowledge Graphs (KGs) continue to penetrate the industrial world after Google's famous "things not strings" was used to explain their acquisition of FreeBase ten years ago. While many KGs exist, they are by and large little more than "entity catalogs", missing entirely the links between those entities. At Google, we recently launched a new enhancement to search that allows product queries, such as "Milk", "Celery" or "12 string guitar", to return local results - places on maps, nearby, that sell the product. The challenge to making this work is that 70% of stores worldwide - and 40% in the US - do not have a web page, Google's primary data source for search. To overcome this challenge and extend our understanding of small to medium-sized brick&mortar shops, we used a unique combination of Knowledge Graphs, AI and Human Common Sense, that demonstrates both the promises and limitations of AI in solving practical business problems.