Discovering Dialog Structure Graph for Open-Domain Dialog Generation
arXiv:2012.15543
Abstract
Learning interpretable dialog structure from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation. In this paper, we conduct unsupervised discovery of dialog structure from chitchat corpora, and then leverage it to facilitate dialog generation in downstream systems. To this end, we present a Discrete Variational Auto-Encoder with Graph Neural Network (DVAE-GNN), to discover a unified human-readable dialog structure. The structure is a two-layer directed graph that contains session-level semantics in the upper-layer vertices, utterance-level semantics in the lower-layer vertices, and edges among these semantic vertices. In particular, we integrate GNN into DVAE to fine-tune utterance-level semantics for more effective recognition of session-level semantic vertex. Furthermore, to alleviate the difficulty of discovering a large number of utterance-level semantics, we design a coupling mechanism that binds each utterance-level semantic vertex with a distinct phrase to provide prior semantics. Experimental results on two benchmark corpora confirm that DVAE-GNN can discover meaningful dialog structure, and the use of dialog structure graph as background knowledge can facilitate a graph grounded conversational system to conduct coherent multi-turn dialog generation.
References in corpus (16)
- Auto-Encoding Variational Bayes
- Categorical Reparameterization with Gumbel-Softmax
- Neural Discrete Representation Learning
- Deep Reinforcement Learning for Dialogue Generation
- Topic Aware Neural Response Generation
- Neural Responding Machine for Short-Text Conversation
- An Information Retrieval Approach to Short Text Conversation
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
- Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
- Proactive Human-Machine Conversation with Explicit Conversation Goals
- Towards a Continuous Knowledge Learning Engine for Chatbots
- A Hierarchical Latent Structure for Variational Conversation Modeling
- Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variables
- Subgoal Discovery for Hierarchical Dialogue Policy Learning
- A Discrete CVAE for Response Generation on Short-Text Conversation