Deep Reinforcement Learning for Dialogue Generation
Citations Over TimeTop 1% of 2016 papers
Abstract
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: informativity, coherence, and ease of answering (related to forward-looking function).We evaluate our model on diversity, length as well as with human judges, showing that the proposed algorithm generates more interactive responses and manages to foster a more sustained conversation in dialogue simulation.This work marks a first step towards learning a neural conversational model based on the long-term success of dialogues.
Related Papers
- → A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Platform(2022)15 cited
- → Cost-Efficient Reinforcement Learning for Optimal Trade Execution on Dynamic Market Environment(2022)2 cited
- Using DataGrid Control to Realize DataBase of Querying in VB6.0(2000)
- Susquehanna Chorale Spring Concert "Roots and Wings"(2017)
- → Classification without gradients: multi-agent reinforcement learning approach to optimization (Conference Presentation)(2023)