Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment

TL;DR

This paper introduces a reinforcement learning-based framework for multi-turn dialogue systems that adaptively control knowledge selection to enhance informativeness and coherence, leading to more meaningful conversations.

Contribution

It proposes a novel Generation-Evaluation framework with a compound reward mechanism for evolving dialogue strategies in knowledge-grounded conversations.

Findings

Outperforms state-of-the-art methods significantly

Demonstrates improved informativeness and coherence in dialogues

Effectively adapts dialogue strategies via reinforcement learning

Abstract

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.