Boosting Naturalness of Language in Task-oriented Dialogues via Adversarial Training

04/30/2020
by   Chenguang Zhu, et al.
0

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

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/23/2017

Adversarial Learning for Neural Dialogue Generation

In this paper, drawing intuition from the Turing test, we propose using ...
research
09/16/2022

Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning

When a natural language generation (NLG) component is implemented in a r...
research
04/23/2018

Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training

Automatic generation of natural language from images has attracted exten...
research
04/29/2020

Counterfactual Off-Policy Training for Neural Response Generation

Learning a neural response generation model on data synthesized under th...
research
09/12/2018

Retrieval-Enhanced Adversarial Training for Neural Response Generation

Dialogue systems are usually built on either generation-based or retriev...
research
09/16/2018

Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

Responses generated by neural conversational models tend to lack informa...
research
09/07/2021

Naturalness Evaluation of Natural Language Generation in Task-oriented Dialogues using BERT

This paper presents an automatic method to evaluate the naturalness of n...

Please sign up or login with your details

Forgot password? Click here to reset