Workflow-Guided Response Generation for Task-Oriented Dialogue

TL;DR

This paper introduces a reinforcement learning framework for task-oriented dialogue systems that ensures generated responses follow specified workflows, improving compliance and naturalness over previous supervised methods.

Contribution

It proposes a novel RL-based approach with a ComplianceScorer to explicitly optimize workflow compliance in dialogue response generation.

Findings

Outperforms baseline methods in compliance and naturalness

Effective on multiple datasets including ABCD and MultiWOZ 2.2

Enhances response quality with explicit workflow adherence

Abstract

Task-oriented dialogue (TOD) systems aim to achieve specific goals through interactive dialogue. Such tasks usually involve following specific workflows, i.e. executing a sequence of actions in a particular order. While prior work has focused on supervised learning methods to condition on past actions, they do not explicitly optimize for compliance to a desired workflow. In this paper, we propose a novel framework based on reinforcement learning (RL) to generate dialogue responses that are aligned with a given workflow. Our framework consists of ComplianceScorer, a metric designed to evaluate how well a generated response executes the specified action, combined with an RL opimization process that utilizes an interactive sampling technique. We evaluate our approach on two TOD datasets, Action-Based Conversations Dataset (ABCD) (Chen et al., 2021a) and MultiWOZ 2.2 (Zang et al., 2020) on a range of automated and human evaluation metrics. Our findings indicate that our RL-based framework outperforms baselines and is effective at enerating responses that both comply with the intended workflows while being expressed in a natural and fluent manner.