The ability of a dialog system to express prespecified language style during conversations has a direct, positive impact on its usability and on user satisfaction. We introduce a new prototype-to-style (PS) framework to tackle the challenge of stylistic dialogue generation. The framework uses an Information Retrieval (IR) system and extracts a response prototype from the retrieved response. A stylistic response generator then takes the prototype and the desired language style as model input to obtain a high-quality and stylistic response. To effectively train the proposed model, we propose a new style-aware learning objective as well as a de-noising learning strategy. Results on three benchmark datasets from two languages demonstrate that the proposed approach significantly outperforms existing baselines in both in-domain and cross-domain evaluations
@article{arxiv.2004.02214,
title = {Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory},
author = {Yixuan Su and Yan Wang and Simon Baker and Deng Cai and Xiaojiang Liu and Anna Korhonen and Nigel Collier},
journal= {arXiv preprint arXiv:2004.02214},
year = {2020}
}