Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings

TL;DR

This paper introduces a scalable dialog response retrieval model that uses Gaussian mixture embeddings to better capture complex, many-to-many relationships between contexts and responses, outperforming existing embedding methods.

Contribution

The paper proposes a novel Gaussian mixture embedding approach for dialog response retrieval that models complex relationships while maintaining scalability.

Findings

Achieves better performance than existing embedding-based methods.

Effectively models complex, many-to-many context-response relationships.

Demonstrates scalability to moderately large response sets.

Abstract

Embedding-based approaches for dialog response retrieval embed the context-response pairs as points in the embedding space. These approaches are scalable, but fail to account for the complex, many-to-many relationships that exist between context-response pairs. On the other end of the spectrum, there are approaches that feed the context-response pairs jointly through multiple layers of neural networks. These approaches can model the complex relationships between context-response pairs, but fail to scale when the set of responses is moderately large (>100). In this paper, we combine the best of both worlds by proposing a scalable model that can learn complex relationships between context-response pairs. Specifically, the model maps the contexts as well as responses to probability distributions over the embedding space. We train the models by optimizing the Kullback-Leibler divergence between the distributions induced by context-response pairs in the training data. We show that the resultant model achieves better performance as compared to other embedding-based approaches on publicly available conversation data.