papers AI Learner
The Github is limit! Click to go to the new site.

Retrieval-Enhanced Adversarial Training for Neural Response Generation

2019-05-23
Qingfu Zhu, Lei Cui, Weinan Zhang, Furu Wei, Ting Liu

Abstract

Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method for neural response generation. Distinct from existing approaches, the REAT method leverages an encoder-decoder framework in terms of an adversarial training paradigm, while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator. An empirical study on a large scale public available benchmark dataset shows that the REAT method significantly outperforms the vanilla Seq2Seq model as well as the conventional adversarial training approach.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1809.04276

PDF

http://arxiv.org/pdf/1809.04276


Comments

Content