Integrating User and Agent Models: A Deep Task-Oriented Dialogue System
This work addresses the problem of improving user experience and robustness in task-oriented dialogue systems for customer service applications, representing an incremental advancement by combining existing techniques in a novel integration.
The paper tackles the limitations of existing task-oriented dialogue systems, which rely on handcrafted components and have limited user simulators, by proposing the SAMIA framework that integrates user and agent models using Seq2Seq learning and deep reinforcement learning, achieving verified effectiveness on a real-world coffee ordering dataset.
Task-oriented dialogue systems can efficiently serve a large number of customers and relieve people from tedious works. However, existing task-oriented dialogue systems depend on handcrafted actions and states or extra semantic labels, which sometimes degrades user experience despite the intensive human intervention. Moreover, current user simulators have limited expressive ability so that deep reinforcement Seq2Seq models have to rely on selfplay and only work in some special cases. To address those problems, we propose a uSer and Agent Model IntegrAtion (SAMIA) framework inspired by an observation that the roles of the user and agent models are asymmetric. Firstly, this SAMIA framework model the user model as a Seq2Seq learning problem instead of ranking or designing rules. Then the built user model is used as a leverage to train the agent model by deep reinforcement learning. In the test phase, the output of the agent model is filtered by the user model to enhance the stability and robustness. Experiments on a real-world coffee ordering dataset verify the effectiveness of the proposed SAMIA framework.