Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment
This work addresses the challenge of improving informativeness and coherence in dialogue systems, which is incremental as it builds on existing reinforcement learning approaches for conversation.
The paper tackles the problem of enhancing multi-turn conversations by developing a Generation-Evaluation framework that uses reinforcement learning to adapt dialogue strategies for better knowledge utilization and coherence, resulting in significant outperformance over state-of-the-art methods.
In this paper, a novel Generation-Evaluation framework is developed for multi-turn conversations with the objective of letting both participants know more about each other. For the sake of rational knowledge utilization and coherent conversation flow, a dialogue strategy which controls knowledge selection is instantiated and continuously adapted via reinforcement learning. Under the deployed strategy, knowledge grounded conversations are conducted with two dialogue agents. The generated dialogues are comprehensively evaluated on aspects like informativeness and coherence, which are aligned with our objective and human instinct. These assessments are integrated as a compound reward to guide the evolution of dialogue strategy via policy gradient. Comprehensive experiments have been carried out on the publicly available dataset, demonstrating that the proposed method outperforms the other state-of-the-art approaches significantly.