Deep Reinforcement Learning for Dialogue Generation

Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes.Modeling the future direction of a dialogue is crucial to generating coherent, interesting dialogues, a need which led traditional NLP models of dialogue to draw on reinforcement learning.In this paper, we show how to integrate these goals, applying deep reinforcement learning to model future reward in chatbot dialogue.The model simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties:…

• NS
  National Science Foundation

  Awards: IIS-1514268, 1464128, 1514268, IIS-1464128
• SF
  Styrelsen för Internationellt Utvecklingssamarbete
• MR
  Microsoft Research
• DA
  Defense Advanced Research Projects Agency
• AR
  Army Research Office

  Awards: W911NF-15-1-, W911NF