Generating Responses with a Specific Emotion in Dialog

Zhenqiao Song, Xiaoqing Zheng, Lu Liu, Mu Xu, Xuanjing Huang

2019 · 144 citations · 33 references

DOIFull text

Open access

Concepts

TL;DR

Dialog systems that can express specific emotions improve usability and user satisfaction, and emotions can be conveyed either by explicit strong words or by implicitly combining neutral words. The authors propose EmoDS, an emotional dialogue system that generates coherent responses while explicitly or implicitly expressing a desired emotion. EmoDS employs a unified framework that structures responses and modulates emotional content through explicit or implicit linguistic choices. Experiments show EmoDS outperforms baselines in BLEU, diversity, and emotional expression quality, confirming that emotions can be conveyed via explicit or implicit language.

Abstract

It is desirable for dialog systems to have capability to express specific emotions during a conversation, which has a direct, quantifiable impact on improvement of their usability and user satisfaction. After a careful investigation of real-life conversation data, we found that there are at least two ways to express emotions with language. One is to describe emotional states by explicitly using strong emotional words; another is to increase the intensity of the emotional experiences by implicitly combining neutral words in distinct ways. We propose an emotional dialogue system (EmoDS) that can generate the meaningful responses with a coherent structure for a post, and meanwhile express the desired emotion explicitly or implicitly within a unified framework. Experimental results showed EmoDS performed better than the baselines in BLEU, diversity and the quality of emotional expression.

References

33