Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

10-2021

Abstract

Task-oriented dialogue agents are built to assist users in completing various tasks. Generating appropriate responses for satisfactory task completion is the ultimate goal. Hence, as a convenient and straightforward way, metrics such as success rate, inform rate etc., have been widely leveraged to evaluate the generated responses. However, beyond task completion, there are several other factors that largely affect user satisfaction, which remain under-explored. In this work, we focus on analyzing different agent behavior patterns that lead to higher user satisfaction scores. Based on the findings, we design a neural response generation model EnRG. It naturally combines the power of pre-trained GPT-2 in response semantic modeling and the merit of dual attention in making use of the external crowd-sourced knowledge. Equipped with two gates via explicit dialogue act modeling, it effectively controls the usage of external knowledge sources in the form of both text and image. We conduct extensive experiments. Both automatic and human evaluation results demonstrate that, beyond comparable task completion, our proposed method manages to generate responses gaining higher user satisfaction.

Keywords

Crowd-sourced knowledge, Response generation, Task-oriented

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Publication

MuCAI '21: Proceedings of the 2nd ACM Multimedia Workshop on Multimodal Conversational AI, Virtual, October 24

First Page

3

Last Page

11

ISBN

9781450386791

Identifier

10.1145/3475959.3485392

Publisher

ACM

City or Country

New York

Copyright Owner and License

Publisher

Additional URL

https://doi.org/10.1145/3475959.3485392

Download

Share

COinS