Generating Dialogue Responses From A Semantic Latent Space

Wei-Jen Ko, Avik Ray, Yilin Shen, Hongxia Jin

TL;DR: A novel dialog generation model that learns on a utterance level semantic latent space. The model could learn from semantically similar sentences collectively, thus eliminates the generic response problem.

Abstract: Generic responses are a known issue for open-domain dialog generation. Most current approaches model this one-to-many task as a one-to-one task, hence being unable to integrate information from multiple semantically similar valid responses of a prompt. We propose a novel dialog generation model that learns a semantic latent space, on which representations of semantically related sentences are close to each other. This latent space is learned by maximizing correlation between the features extracted from prompt and responses. Learning the pair relationship between the prompts and responses as a regression task on the latent space, instead of classification on the vocabulary using MLE loss, enables our model to view semantically related responses collectively. An additional autoencoder is trained, for recovering the full sentence from the latent space. Experimental results show that our proposed model eliminates the generic response problem, while achieving comparable or better coherence compared to baselines.

Keywords: dialog, chatbot, open domain conversation, CCA