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.- Anthology ID:
- P19-1366
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3763–3773
- Language:
- URL:
- https://aclanthology.org/P19-1366
- DOI:
- 10.18653/v1/P19-1366
- Cite (ACL):
- Qingfu Zhu, Lei Cui, Wei-Nan Zhang, Furu Wei, and Ting Liu. 2019. Retrieval-Enhanced Adversarial Training for Neural Response Generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3763–3773, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Retrieval-Enhanced Adversarial Training for Neural Response Generation (Zhu et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/P19-1366.pdf