Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
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.
Code (4)
Tasks
Conversational Response GenerationDiversityInformativenessSimilar Papers 제목 키워드 기반
Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training
In this paper, we propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better. In contrast to standard adversarial training algor…
Dialogue GenerationDiversityResponse GenerationKnowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model
End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus. However, one of the fatal drawbacks in such approaches is that they are u…
Dialogue GenerationResponse GenerationDiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation
Having engaging and informative conversations with users is the utmost goal for open-domain conversational systems. Recent advances in transformer-based language models and their applications to dialogue systems have suc…
Response GenerationKECRS: Towards Knowledge-Enriched Conversational Recommendation System
The chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions. To better understand user's intentions, external knowledge graphs (KG) have bee…
Conversational RecommendationEntity EmbeddingsKnowledge GraphsRecommendation Systems+2Posterior-GAN: Towards Informative and Coherent Response Generation with Posterior Generative Adversarial Network
Neural conversational models learn to generate responses by taking into account the dialog history. These models are typically optimized over the query-response pairs with a maximum likelihood estimation objective. Howev…
DecoderGenerative Adversarial NetworkInformativenessResponse Generation