Evorus Combines AI and Crowd Sourcing for a Smarter Chatbot

Carnegie Mellon University researchers say they “have created a conversational agent that is tough to stump.” How? By adding humans into the mix. The chatbot system is called Evorus. A post on Carnegie Mellon’s website says, “What sets it apart, says Jeff Bigham, associate professor in the Human-Computer Interaction Institute, is that humans are simultaneously training the system's artificial intelligence, making it gradually less dependent on people.”

Evorus follows in the footsteps on an earlier CMU agent called Chorus, and “recruits crowd workers on demand from Amazon Mechanical Turk to answer questions from users, with the crowd workers voting on the best answer. Evorus also keeps track of questions asked and answered and, over time, begins to suggest these answers for subsequent questions. The researchers also have developed a process by which the AI can help to approve a message with less crowd worker involvement.”

Evorus is available for download to anyone willing to help in the research process as the system continues to evolve.

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues