Weekly QuEST Discussion Topics, 25 Jan
QuEST 25 Jan 2019
QuEST this week will be focused on conversational bots – social bots – specifically an approach by colleagues at Facebook and Stanford:
Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
arXiv:1901.05415v1 [cs.CL] 16 Jan 2019
• The majority of conversations a dialogue agent sees over its lifetime occur after it has already been trained and deployed, leaving a vast store of potential training signal untapped. In this work, we propose the self-feeding chatbot, a dialogue agent with the ability to extract new training examples from the conversations it participates in.
• As our agent engages in conversation, it also estimates user satisfaction in its responses. When the conversation appears to be going well, the user’s responses become new training examples to imitate.
• When the agent believes it has made a mistake, it asks for feedback; learning to predict the feedback that will be given improves the chatbot’s dialogue abilities further.
• On the PERSONACHAT chit-chat dataset with over 131k training examples, we find that learning from dialogue with a self-feeding chatbot significantly improves performance, regardless of the amount of traditional supervision.