Cross Copy Network for Dialogue Generation
This addresses the need for logical consistency in dialogue generation for domains like customer service and court debates, though it is incremental as it builds on existing sequence-to-sequence methods.
The paper tackles the problem of generating dialogue content that incorporates logical structure, which is often ignored in existing models, by proposing Cross Copy Networks (CCN) to use context and similar instances' logic. Experiments on court debate and customer service tasks show the algorithm outperforms state-of-the-art models.
In the past few years, audiences from different fields witness the achievements of sequence-to-sequence models (e.g., LSTM+attention, Pointer Generator Networks, and Transformer) to enhance dialogue content generation. While content fluency and accuracy often serve as the major indicators for model training, dialogue logics, carrying critical information for some particular domains, are often ignored. Take customer service and court debate dialogue as examples, compatible logics can be observed across different dialogue instances, and this information can provide vital evidence for utterance generation. In this paper, we propose a novel network architecture - Cross Copy Networks(CCN) to explore the current dialog context and similar dialogue instances' logical structure simultaneously. Experiments with two tasks, court debate and customer service content generation, proved that the proposed algorithm is superior to existing state-of-art content generation models.