Retrieval-based Goal-Oriented Dialogue Generation
This work addresses goal-oriented dialogue generation for customer support applications, presenting an incremental hybrid approach.
The paper tackles goal-oriented dialogue generation by combining retrieval from past history with a hierarchical neural encoder-decoder architecture, showing significant improvements in human-rated appropriateness and fluency, and achieving competitive state-of-the-art results without requiring explicit past machine act labels.
Most research on dialogue has focused either on dialogue generation for openended chit chat or on state tracking for goal-directed dialogue. In this work, we explore a hybrid approach to goal-oriented dialogue generation that combines retrieval from past history with a hierarchical, neural encoder-decoder architecture. We evaluate this approach in the customer support domain using the Multiwoz dataset (Budzianowski et al., 2018). We show that adding this retrieval step to a hierarchical, neural encoder-decoder architecture leads to significant improvements, including responses that are rated more appropriate and fluent by human evaluators. Finally, we compare our retrieval-based model to various semantically conditioned models explicitly using past dialog act information, and find that our proposed model is competitive with the current state of the art (Chen et al., 2019), while not requiring explicit labels about past machine acts.