arXiv (Cornell University) · 2018 · 181 citations · 0 references
ComputingComputer ScienceData ScienceFeature EngineeringMachine LearningNatural Language ProcessingConversation AnalysisDeep LearningDialogue SystemsGenerative ModelingLanguage ModelingOptimization For Machine LearningAdversarial Question AnsweringDialogue Response GenerationGenerative Adversarial NetworksGenerative Response GenerationMutual Information EstimationNeural Language ModelsQuery-response MatchingResponse Diversity
Responses generated by neural conversational models tend to lack informativeness and diversity. We present Adversarial Information Maximization (AIM), an adversarial learning strategy that addresses these two related but distinct problems. To foster response diversity, we leverage adversarial training that allows distributional matching of synthetic and real responses. To improve informativeness, our framework explicitly optimizes a variational lower bound on pairwise mutual information between query and response. Empirical results from automatic and human evaluations demonstrate that our methods significantly boost informativeness and diversity.