DeepAI AI Chat
Log In Sign Up

Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory

by   Yixuan Su, et al.

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


Stylistic Retrieval-based Dialogue System with Unparallel Training Data

The ability of a dialog system to express consistent language style duri...

Response Generation by Context-aware Prototype Editing

Open domain response generation has achieved remarkable progress in rece...

Stylistic Dialogue Generation via Information-Guided Reinforcement Learning Strategy

Stylistic response generation is crucial for building an engaging dialog...

Stylized Dialogue Response Generation Using Stylized Unpaired Texts

Generating stylized responses is essential to build intelligent and enga...

StyleDGPT: Stylized Response Generation with Pre-trained Language Models

Generating responses following a desired style has great potentials to e...

Style-Aware Contrastive Learning for Multi-Style Image Captioning

Existing multi-style image captioning methods show promising results in ...

Proximal Policy Optimization for Improved Convergence in IRGAN

IRGAN is an information retrieval (IR) modeling approach that uses a the...