Researchers from Stanford University have released the second edition of the Stanford Question Answering Dataset (SQuAD) to help AI, such as Siri, learn when it lacks enough information to answer a question accurately. The dataset consists of over 50,000 unanswerable questions designed to appear answerable based off information in the accompanying paragraphs. Humans can easily identify when a question is unanswerable, but AI systems have a harder time, which limits the ability of automated assistants and other services to accurately respond to users’ queries. For example, when asked who the King of England is, a human would recognize that England does not have a king, while AI systems are more likely to say the deceased King George VI, who was the last King of the United Kingdom.
Teaching AI to Know When it is Stumped
Michael McLaughlin is a research assistant at the Center for Data Innovation. He previously worked at Oracle and held internships at USA TODAY and in local government. Prior to joining the Center for Data Innovation, Michael graduated from Wake Forest University, where he majored in Communication with Minors in Politics and International Affairs and Journalism. He is currently pursuing his Master’s in Communication at Stanford University, specializing in Data Journalism.
View all posts by Michael McLaughlin