面向低资源任务型对话系统的多分支对偶学习
Multijugate Dual Learning for Low-Resource Task-Oriented Dialogue System
AI总结:
本文提出多分支对偶学习方法,通过挖掘不确定话语与确定性对话状态之间的对齐信息,在不增加参数的前提下提升低资源任务型对话系统的数据利用效率和泛化能力,并在多个基准上取得最优结果。
摘要:
真实场景中的对话数据往往稀疏可得,导致数据匮乏的端到端对话系统训练不充分。我们发现,在低资源场景下,通过挖掘不确定话语与确定性对话状态之间的对齐信息,可以提升数据利用效率。因此,我们创新性地在任务型对话中引入对偶学习,以利用异构数据之间的相关性。此外,我们将一对一的对偶关系转换为多分支对偶关系,以降低对偶训练中虚假相关对泛化能力的影响。在不引入额外参数的情况下,我们的方法可以应用于任意网络结构。大量实证分析表明,所提出的方法在多个基准上提升了端到端任务型对话系统的有效性,并在低资源场景下取得了最先进的结果。
英文摘要:
Dialogue data in real scenarios tend to be sparsely available, rendering data-starved end-to-end dialogue systems trained inadequately. We discover that data utilization efficiency in low-resource scenarios can be enhanced by mining alignment information uncertain utterance and deterministic dialogue state. Therefore, we innovatively implement dual learning in task-oriented dialogues to exploit the correlation of heterogeneous data. In addition, the one-to-one duality is converted into a multijugate duality to reduce the influence of spurious correlations in dual training for generalization. Without introducing additional parameters, our method could be implemented in arbitrary networks. Extensive empirical analyses demonstrate that our proposed method improves the effectiveness of end-to-end task-oriented dialogue systems under multiple benchmarks and obtains state-of-the-art results in low-resource scenarios.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。