Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
This addresses the problem of understanding dialog generation processes for developers and users, though it is incremental as it builds upon existing VAEs and encoder-decoder frameworks.
The paper tackles the lack of interpretability in encoder-decoder dialog models by proposing unsupervised discrete sentence representation learning methods, which integrate with existing models to enable interpretable response generation and have been validated on real-world datasets.
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.