​Learning from Dialogue after Deployment: Feed Yourself, Chatbot!

From abstract: The self-feeding chatbot, a dialogue agent with the ability to extract new training examples from the conversations it participates in.

This is an article about chatbot which is capable of true online learning. There is also a venturebeat article on the subject, covering the perspective: «Facebook and Stanford researchers design a chatbot that learns from its mistakes».

Venturebeat: https://venturebeat.com/2019/01/17/facebook-and-stanford-researchers-design-a-chatbot-that-learns-from-its-mistakes/
ArXiV: https://arxiv.org/abs/1901.05415

#NLP #chatbot #facebook #Stanford

🔗 Facebook and Stanford researchers design a chatbot that learns from its mistakes
Chatbots rarely make great conversationalists. With the exception of perhaps Microsoft’s Xiaoice in China, which has about 40 million users and averages 23 back-and-forth exchanges, and Alibaba’s Dian Xiaomi, an automated sales agent that serves nearly 3.5 million customers a day, most can’t hold humans’ attention for much longer than 15 minutes. But that’s not tempering bot adoption any — in fact