Facebook AI Research has announced a new generation of their Blenderbot chatbot, Blenderbot 2.0. The main new feature is the addition of long term memory and the ability to search the internet for more information. It’s a significant update to the original BlenderBot and can have sophisticated conversations on nearly any topic.
Blenderbot 2.0 takes pertinent information gleaned during conversation and stores it in a long-term memory so it can then leverage this knowledge in ongoing conversations that may continue for days, weeks, or even months. The knowledge is stored separately for each person it speaks with, which ensures that no new information learned in one conversation is used in another.
During conversation, the model can generate contextual internet search queries via the Bing Search API, read the results, and incorporate that information when responding to people’s questions and comments. This means the model stays up-to-date in an ever-changing world.
Blenderbot combines several conversational skills — like personality, empathy, and knowledge — into a single system and when talking to people, BlenderBot 2.0 demonstrated that it’s better at conducting longer, more knowledgeable, and factually consistent conversations over multiple sessions.
You cant speak to Blenderbot 2.0 yet, but Facebook has released the complete model, code, and evaluation setup, as well as two new conversational data sets — human conversations bolstered by internet searches, and multisession chats with people that reference previous sessions — used to train the model, so other researchers can reproduce this work and advance conversational AI research.
Find out more at Facebook here.