EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble Model on Short-Text Conversation
arXiv:2004.14592
Abstract
Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and cons. Despite the natural idea of an ensemble model of the two, existing ensemble methods only focused on leveraging one approach to enhance another, we argue however that they can be further mutually enhanced with a proper training strategy. In this paper, we propose ensembleGAN, an adversarial learning framework for enhancing a retrieval-generation ensemble model in open-domain conversation scenario. It consists of a language-model-like generator, a ranker generator, and one ranker discriminator. Aiming at generating responses that approximate the ground-truth and receive high ranking scores from the discriminator, the two generators learn to generate improved highly relevant responses and competitive unobserved candidates respectively, while the discriminative ranker is trained to identify true responses from adversarial ones, thus featuring the merits of both generator counterparts. The experimental results on a large short-text conversation data demonstrate the effectiveness of the ensembleGAN by the amelioration on both human and automatic evaluation metrics.
arXiv comment10 pages, SIGIR 2019
References in corpus (8)
- Conditional Generative Adversarial Nets
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- Adversarial Ranking for Language Generation
- RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems
- Towards Diverse and Natural Image Descriptions via a Conditional GAN
- DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
- Neural Response Generation with Dynamic Vocabularies