A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
This addresses the challenge of low-resource knowledge-grounded dialogue generation for AI systems, offering a novel framework that reduces data dependency, though it is incremental in improving existing methods.
The paper tackles the problem of building knowledge-grounded dialogue systems with limited training data by proposing a three-stage learning framework that leverages weakly supervised learning from ungrounded dialogues and unstructured knowledge. The approach outperforms state-of-the-art methods with less data and performs well in zero-resource scenarios, as shown on two benchmarks.
Neural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge. Nevertheless, it is laborious to construct such knowledge-grounded dialogues, and existing models usually perform poorly when transfer to new domains with limited training samples. Therefore, building a knowledge-grounded dialogue system under the low-resource setting is a still crucial issue. In this paper, we propose a novel three-stage learning framework based on weakly supervised learning which benefits from large scale ungrounded dialogues and unstructured knowledge base. To better cooperate with this framework, we devise a variant of Transformer with decoupled decoder which facilitates the disentangled learning of response generation and knowledge incorporation. Evaluation results on two benchmarks indicate that our approach can outperform other state-of-the-art methods with less training data, and even in zero-resource scenario, our approach still performs well.