Log In Sign Up

Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training

by   Wangchunshu Zhou, et al.

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 algorithms, IAT encourages the model to be sensitive to the perturbation in the dialogue history and therefore learning from perturbations. By giving higher rewards for responses whose output probability reduces more significantly when dialogue history is perturbed, the model is encouraged to generate more diverse and consistent responses. By penalizing the model when generating the same response given perturbed dialogue history, the model is forced to better capture dialogue history and generate more informative responses. Experimental results on two benchmark datasets show that our approach can better model dialogue history and generate more diverse and consistent responses. In addition, we point out a problem of the widely used maximum mutual information (MMI) based methods for improving the diversity of dialogue response generation models and demonstrate it empirically.


page 1

page 2

page 3

page 4


Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation

Personalized dialogue systems explore the problem of generating response...

An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation

In this work, we propose a method for neural dialogue response generatio...

Learning to Predict Persona Information forDialogue Personalization without Explicit Persona Description

Personalizing dialogue agents is important for dialogue systems to gener...

NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation

Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular...

Multi-Referenced Training for Dialogue Response Generation

In open-domain dialogue response generation, a dialogue context can be c...

Counterfactual Off-Policy Training for Neural Response Generation

Learning a neural response generation model on data synthesized under th...

Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation

Dialogue generation models face the challenge of producing generic and r...