MIT Technology Review Subscribe

Facebook’s experimental chatbot is learning to do small talk

A chatbot trained to engage its partner on personal topics can learn to predict information about the other participant.

Background: Even with AI, chatbots are brittle systems that typically can’t talk about anything outside of what they’ve been trained on. They also tend not to have a personality or long-term memory, so most development for chat agents is around task-specific goals, like airline bookings.

Advertisement

Once more, with feeling: A new paper by Facebook AI Research demonstrates a way to create a bot that is good at general conversation, a.k.a. chit chat. Trained on a new data set consisting of 164,356 utterances between crowdsourced workers who were asked to chat, the system can store a persona in a memory-augmented neural network and produce “more personal, specific, consistent and engaging responses.”

This story is only available to subscribers.

Don’t settle for half the story.
Get paywall-free access to technology news for the here and now.

Subscribe now Already a subscriber? Sign in
You’ve read all your free stories.

MIT Technology Review provides an intelligent and independent filter for the flood of information about technology.

Subscribe now Already a subscriber? Sign in

Getting to know you: Using the same setup, the chatbot asks its dialogue partner questions about personal topics, which it can then use to build a model of the partner. Human evaluators still ranked human partners much higher across board for things like persona and consistency, but this model outscored one trained on movie dialogue—one of the largest dialogue data sets out there.

This is your last free story.
Sign in Subscribe now

Your daily newsletter about what’s up in emerging technology from MIT Technology Review.

Please, enter a valid email.
Privacy Policy
Submitting...
There was an error submitting the request.
Thanks for signing up!

Our most popular stories

Advertisement