A Simple Language Model for Task-Oriented Dialogue

TLDR

Task‑oriented dialogue is typically split into user understanding, action selection, and response generation. SimpleTOD trains a single causal language model on all sub‑tasks cast as sequence prediction, leveraging transfer learning from pre‑trained models such as GPT‑2. SimpleTOD achieves state‑of‑the‑art results on MultiWOZ, boosting joint goal accuracy by 0.49 points and raising inform, success, and combined scores by 8.1, 9.7, and 7.2 points respectively.

Abstract

Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified approach leads to state-of-the-art performance on the MultiWOZ dataset. SimpleTOD is a simple approach to task-oriented dialogue that uses a single causal language model trained on all sub-tasks recast as a single sequence prediction problem. This allows SimpleTOD to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2. SimpleTOD improves over the prior state-of-the-art by 0.49 points in joint goal accuracy for dialogue state tracking. More impressively, SimpleTOD also improves the main metrics used to evaluate action decisions and response generation in an end-to-end setting for task-oriented dialog systems: inform rate by 8.1 points, success rate by 9.7 points, and combined score by 7.2 points.