A Hierarchical Latent Structure for Variational Conversation Modeling

Abstract

Variational autoencoders (VAE) combined with hierarchical RNNs have emerged as a powerful framework for conversation modeling. However, they suffer from the notorious degeneration problem, where the decoders learn to ignore latent variables and reduce to vanilla RNNs. We empirically show that this degeneracy occurs mostly due to two reasons. First, the expressive power of hierarchical RNN decoders is often high enough to model the data using only its decoding distributions without relying on the latent variables. Second, the conditional VAE structure whose generation process is conditioned on a context, makes the range of training targets very sparse; that is, the RNN decoders can easily overfit to the training data ignoring the latent variables. To solve the degeneration problem, we propose a novel model named Variational Hierarchical Conversation RNNs (VHCR), involving two key ideas of (1) using a hierarchical structure of latent variables, and (2) exploiting an utterance drop regularization. With evaluations on two datasets of Cornell Movie Dialog and Ubuntu Dialog Corpus, we show that our VHCR successfully utilizes latent variables and outperforms state-of-the-art models for conversation generation. Moreover, it can perform several new utterance control tasks, thanks to its hierarchical latent structure.

arXiv commentPublished in NAACL 2018 (Oral)

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• A Neural Conversational Model
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• Variational Lossy Autoencoder
• Adversarial Learning for Neural Dialogue Generation

Cited by in corpus (8)

• Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
• DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
• Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
• A Tutorial on Deep Latent Variable Models of Natural Language
• Discovering Dialog Structure Graph for Open-Domain Dialog Generation
• Towards Multimodal Response Generation with Exemplar Augmentation and Curriculum Optimization
• Injecting Hierarchy with U-Net Transformers
• Memory-Augmented Recurrent Networks for Dialogue Coherence