Cross Copy Network for Dialogue Generation

TL;DR

This paper introduces Cross Copy Networks, a novel architecture for dialogue generation that leverages dialogue logic from similar instances, improving over existing models especially in domain-specific contexts.

Contribution

The paper proposes a new Cross Copy Network architecture that incorporates dialogue logic from similar instances to enhance content generation in dialogue systems.

Findings

Outperforms state-of-the-art models in court debate and customer service tasks.

Effectively captures dialogue logic across instances.

Improves relevance and coherence in generated dialogues.

Abstract

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.