• DOI:10.18653/v1/P19-1366
Corpus ID: 52195919

Retrieval-Enhanced Adversarial Training for Neural Response Generation

@inproceedings{Zhu2019RetrievalEnhancedAT,
  title={Retrieval-Enhanced Adversarial Training for Neural Response Generation},
  author={Qingfu Zhu and Lei Cui and W. Zhang and Furu Wei and Yi-ning Chen and T. Liu},
  booktitle={ACL},
  year={2019}
}

Qingfu Zhu, Lei Cui, +3 authors T. Liu

Published in ACL 2019

Computer Science

Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. [...] Key Method 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…Expand Abstract

View on ACL

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed