Cross Copy Network for Dialogue Generation

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.

arXiv comment11 pages, 4 figures

References in corpus (14)

• Sequence to Sequence Learning with Neural Networks
• ADADELTA: An Adaptive Learning Rate Method
• Convolutional Sequence to Sequence Learning
• Pointer Sentinel Mixture Models
• Machine Comprehension Using Match-LSTM and Answer Pointer
• Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
• Neural Machine Translation in Linear Time
• Get To The Point: Summarization with Pointer-Generator Networks
• The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service
• Proactive Human-Machine Conversation with Explicit Conversation Goals
• Language as a Latent Variable: Discrete Generative Models for Sentence Compression
• Hierarchical Pointer Net Parsing
• Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
• Extending Neural Generative Conversational Model using External Knowledge Sources