Multijugate Dual Learning for Low-Resource Task-Oriented Dialogue System
This work addresses data scarcity for low-resource task-oriented dialogue systems, representing an incremental improvement through a novel method for a known bottleneck.
The paper tackles the problem of training end-to-end task-oriented dialogue systems with sparse data by enhancing data utilization efficiency through dual learning and multijugate duality, achieving state-of-the-art results in low-resource scenarios on multiple benchmarks.
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.