Log In Sign Up

Stylistic Retrieval-based Dialogue System with Unparallel Training Data

by   Hao Fu, et al.

The ability of a dialog system to express consistent language style during conversations has a direct, positive impact on its usability and on user satisfaction. Although previous studies have demonstrated that style transfer is feasible with a large amount of parallel data, it is often impossible to collect such data for different styles. In this paper, instead of manually constructing conversation data with a certain style, we propose a flexible framework that adapts a generic retrieval-based dialogue system to mimic the language style of a specified persona without any parallel data. Our approach is based on automatic generation of stylized data by learning the usage of jargon, and then rewriting the generic conversations to a stylized one by incorporating the jargon. In experiments we implemented dialogue systems with five distinct language styles, and the result shows our framework significantly outperforms baselines in terms of the average score of responses' relevance and style degree, and content diversity. A/B testing on a commercial chatbot shows that users are more satisfied with our system. This study demonstrates the feasibility of building stylistic dialogue systems by simple data augmentation.


page 1

page 2

page 3

page 4


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

The ability of a dialog system to express prespecified language style du...

Structuring Latent Spaces for Stylized Response Generation

Generating responses in a targeted style is a useful yet challenging tas...

External Knowledge Selection with Weighted Negative Sampling in Knowledge-grounded Task-oriented Dialogue Systems

Constructing a robust dialogue system on spoken conversations bring more...

Multi-dimensional Style Transfer for Partially Annotated Data using Language Models as Discriminators

Style transfer has been widely explored in natural language generation w...

Mitigating Negative Style Transfer in Hybrid Dialogue System

As the functionality of dialogue systems evolves, hybrid dialogue system...

Audience-Centric Natural Language Generation via Style Infusion

Adopting contextually appropriate, audience-tailored linguistic styles i...

Stylistic Dialogue Generation via Information-Guided Reinforcement Learning Strategy

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