论文标题
UBARV2：旨在减轻以任务为导向的对话中的暴露偏见
UBARv2: Towards Mitigating Exposure Bias in Task-Oriented Dialogs
论文作者
论文摘要
本文研究了以任务为导向的对话系统中的曝光偏差问题，该模型在多个转盘上生成的内容驱动对话框上下文从训练时间的地面确实分布驱动，从而引入了错误传播并损害了TOD系统的鲁棒性。为了弥合训练和推理多转弯任务导向对话框之间的差距，我们建议会话级抽样，该采样将模型明确地暴露于培训期间对话框上下文的采样内容。此外，我们采用基于辍学的一致性正规化与屏蔽策略R掩码，以进一步提高模型的鲁棒性和性能。拟议的UBARV2在标准化评估基准多WOZ上实现了最先进的性能，并且广泛的实验显示了所提出方法的有效性。
This paper studies the exposure bias problem in task-oriented dialog systems, where the model's generated content over multiple turns drives the dialog context away from the ground-truth distribution at training time, introducing error propagation and damaging the robustness of the TOD system. To bridge the gap between training and inference for multi-turn task-oriented dialogs, we propose session-level sampling which explicitly exposes the model to sampled generated content of dialog context during training. Additionally, we employ a dropout-based consistency regularization with the masking strategy R-Mask to further improve the robustness and performance of the model. The proposed UBARv2 achieves state-of-the-art performance on the standardized evaluation benchmark MultiWOZ and extensive experiments show the effectiveness of the proposed methods.
