Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation

Abstract

The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains. Yet it is limited because it cannot output interpretable actions as in traditional systems, which hinders humans from understanding its generation process. We present an unsupervised discrete sentence representation learning method that can integrate with any existing encoder-decoder dialog models for interpretable response generation. Building upon variational autoencoders (VAEs), we present two novel models, DI-VAE and DI-VST that improve VAEs and can discover interpretable semantics via either auto encoding or context predicting. Our methods have been validated on real-world dialog datasets to discover semantic representations and enhance encoder-decoder models with interpretable generation.

arXiv commentAccepted as a long paper in ACL 2018

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Categorical Reparameterization with Gumbel-Softmax
• Neural Discrete Representation Learning
• Recurrent Neural Network Regularization
• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• InfoVAE: Information Maximizing Variational Autoencoders
• A Persona-Based Neural Conversation Model
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Toward Controlled Generation of Text
• Adversarially Regularized Autoencoders
• Latent Variable Dialogue Models and their Diversity
• Latent Intention Dialogue Models
• Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction

Cited by in corpus (12)

• Avoiding Latent Variable Collapse With Generative Skip Models
• MALA: Cross-Domain Dialogue Generation with Action Learning
• Dirichlet Variational Autoencoder for Text Modeling
• Unsupervised Dialog Structure Learning
• Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
• Neural Response Generation with Meta-Words
• Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
• Generative Dual Adversarial Network for Generalized Zero-shot Learning
• MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data
• A Batch Normalized Inference Network Keeps the KL Vanishing Away
• Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure
• When is it permissible for artificial intelligence to lie? A trust-based approach