IBM, U. of Michigan Creating Chatty Computer

IBM and the University of Michigan are working on a conversational computing system that will transform human-machine communication.

IBM logo

How would you like to have a conversation with your computer to plan your vacation or to do your taxes, or literally hold a discussion with your car about the best way to get home through traffic? Well, if a new project from IBM and the University of Michigan goes as planned, that may not be so far off.

Sure, it is possible to "talk" to PCs, cars, smartphones and other devices today, but the interaction is limited to rote question and answering. What the University of Michigan and IBM have in mind is the ability to hold real conversations with these systems "on human terms," the university said.

The University of Michigan and IBM have launched a $4.5 million collaboration to develop a new class of conversational technologies that will enable people to interact more naturally and effectively with computers. The multiyear partnership is expected to usher in the next frontier of artificial intelligence (AI)-based dialog management that will transform human-machine communication.

Indeed, in an effort known as Project Sapphire, IBM and the University of Michigan Artificial Intelligence Lab will develop a cognitive system that functions as an academic advisor for undergraduate computer science and engineering majors at the university. The system will enable researchers to explore how smart machines interact with people in goal-driven dialogues.

To do this, the team will capture and annotate large volumes of approved recorded human-to-human conversations between undergraduates and their advisors on topics such as course selection, career advice, extracurricular recommendations and homework resources. The researchers in the student advisor project will have access to transcripts of thousands of counseling sessions between students and human advisors, wrote Steve Hamm, IBM chief storyteller, in a blog post on the project. The team will use these conversations to train the system on how to respond to interactions with students, and ultimately learn how to automatically navigate and successfully reply in conversations with those using the system.

"Human-to-machine interactions, similar to human-to-human conversations, are rarely confined to one question and one answer," said David Nahamoo, IBM fellow and chief technologist for conversational systems on the IBM Watson team, in a statement. "They involve multiple turns of a conversation with responses that can be imprecise and unclear, making it difficult to simulate the human experience. By partnering with the University of Michigan, we have an enormous opportunity to apply AI technologies in new ways and transform human-machine communication. This collaboration marks the next chapter in a longstanding relationship between the University and IBM to place the power of cognitive technologies into the hands of the next generation of thinkers."

Moreover, unlike rules-based interactive virtual assistant systems that are programmed with hard-coded responses and scripted replies, Project Sapphire will apply probabilistic and statistical methods of reasoning that understand conditions and context, IBM said. By employing deep learning, machine learning, reinforcement learning, natural language understanding, knowledge representation, emotion analysis and software technologies, the cognitive system will be trained using the recorded human-to-human conversations and will continue to learn and improve with increased interaction.

"Natural conversations bring in so many different aspects of human intelligence—knowledge, context, goals and emotion, for instance. In many ways, to build a versatile conversational system is a grand challenge for artificial intelligence," said Satinder Singh Baveja, professor of computer science and engineering and director of the University of Michigan's AI Lab, in a statement. "We look forward to taking it on with this partnership."