An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation
This addresses the need for transparent decision-making in task-oriented dialogues, offering an incremental improvement over existing neuro-symbolic methods.
The paper tackles the interpretability problem in neural-based task-oriented dialogue systems by proposing a two-phase neuro-symbolic framework that generates and verifies hypotheses to enable explicit reasoning chains, achieving better results on two benchmark datasets.
We study the interpretability issue of task-oriented dialogue systems in this paper. Previously, most neural-based task-oriented dialogue systems employ an implicit reasoning strategy that makes the model predictions uninterpretable to humans. To obtain a transparent reasoning process, we introduce neuro-symbolic to perform explicit reasoning that justifies model decisions by reasoning chains. Since deriving reasoning chains requires multi-hop reasoning for task-oriented dialogues, existing neuro-symbolic approaches would induce error propagation due to the one-phase design. To overcome this, we propose a two-phase approach that consists of a hypothesis generator and a reasoner. We first obtain multiple hypotheses, i.e., potential operations to perform the desired task, through the hypothesis generator. Each hypothesis is then verified by the reasoner, and the valid one is selected to conduct the final prediction. The whole system is trained by exploiting raw textual dialogues without using any reasoning chain annotations. Experimental studies on two public benchmark datasets demonstrate that the proposed approach not only achieves better results, but also introduces an interpretable decision process.