CLJun 23, 2019

DAL: Dual Adversarial Learning for Dialogue Generation

arXiv:1906.09556v11096 citations
Originality Incremental advance
AI Analysis

This addresses the issue of low-quality responses in dialogue systems for users, though it appears incremental as it builds on existing generative approaches.

The paper tackled the problems of generating safe and unnatural responses in open-domain dialogue systems by proposing the Dual Adversarial Learning (DAL) framework, which improved diversity and overall quality of responses, outperforming state-of-the-art methods in automatic metrics and human evaluations.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes