Boosting Naturalness of Language in Task-oriented Dialogues via Adversarial Training
Chenguang Zhu · 2020
The natural language generation (NLG) module in a task-oriented dialogue system produces user-facing utterances conveying required information.Thus, it is critical for the generated response to be natural and fluent.We propose to integrate adversarial training to produce more human-like responses.The model uses Straight-Through Gumbel-Softmax estimator for gradient computation.We also propose a two-stage training scheme to boost performance.Empirical results show that the adversarial training can effectively improve the quality of language generation in both automatic and human evaluations.For example, in the RNN-LG Restaurant dataset, our model AdvNLG outperforms the previous state-of-the-art result by 3.6% in BLEU.