Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation
This addresses the issue of inconsistent persona in dialogue systems for applications like chatbots, but it is incremental as it builds on existing persona-based models.
The authors tackled the problem of generating personality-consistent dialogue responses by proposing a three-stage generate-delete-rewrite framework, which improved performance on the Persona-Chat dataset as shown by human and automatic evaluations.
Maintaining a consistent personality in conversations is quite natural for human beings, but is still a non-trivial task for machines. The persona-based dialogue generation task is thus introduced to tackle the personality-inconsistent problem by incorporating explicit persona text into dialogue generation models. Despite the success of existing persona-based models on generating human-like responses, their one-stage decoding framework can hardly avoid the generation of inconsistent persona words. In this work, we introduce a three-stage framework that employs a generate-delete-rewrite mechanism to delete inconsistent words from a generated response prototype and further rewrite it to a personality-consistent one. We carry out evaluations by both human and automatic metrics. Experiments on the Persona-Chat dataset show that our approach achieves good performance.