DAL: Dual Adversarial Learning for Dialogue Generation

2019-06-23 · WS 2019 6 · Shaobo Cui, Rongzhong Lian, Di Jiang, Yuanfeng Song, Siqi Bao, Yong Jiang

In open-domain dialogue systems, generative approaches have attracted much attention for response generation. However, existing methods are heavily plagued by generating safe responses and unnatural responses. To alleviate these two problems, we propose a novel framework named Dual Adversarial Learning (DAL) for high-quality response generation. DAL is the first work to innovatively utilizes the duality between query generation and response generation to avoid safe responses and increase the diversity of the generated responses. Additionally, DAL uses adversarial learning to mimic human judges and guides the system to generate natural responses. Experimental results demonstrate that DAL effectively improves both diversity and overall quality of the generated responses. DAL outperforms the state-of-the-art methods regarding automatic metrics and human evaluations.

📄 PDF Abstract BibTeX arXiv:1906.09556

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue GenerationDiversityResponse Generation

Adversarial Learning for Neural Dialogue Generation

2017-01-23 · EMNLP 2017 9 · Jiwei Li, Will Monroe, Tianlin Shi, Sébastien Jean 외

In this paper, drawing intuition from the Turing test, we propose using adversarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishable from human-generated…

Dialogue Evaluation Dialogue Generation Reinforcement Learning Reinforcement Learning (RL)

Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning

2018-12-09 · Ziming Li, Julia Kiseleva, Maarten de Rijke

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may l…

Dialogue Generation Imitation Learning reinforcement-learning Reinforcement Learning+1

Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning

2020-04-19 · Hongcai Xu, Junpeng Bao, Gaojie Zhang

Knowledge graph-based dialogue systems are capable of generating more informative responses and can implement sophisticated reasoning mechanisms. However, these models do not take into account the sparseness and incomple…

Adversarial Attack Dialogue Generation Meta-Learning

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

2021-05-31 · ACL 2021 5 · Wangchunshu Zhou, Qifei Li, Chenle Li

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 Generation Diversity Response Generation

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

2019-01-22 · Xiang Kong, Bohan Li, Graham Neubig, Eduard Hovy 외

In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment…

Dialogue Generation Response Generation Vocal Bursts Intensity Prediction