The Effect of Multiple Replies for Natural Language Generation Chatbots

Abstract

Among the NLP models’ usages, some applications provide multiple output options, and some offer only a single result to the end-users. However, there is little research about which situations providing multiple outputs from NLP models will benefit the user experience. Therefore, in this position paper, we summarize the progress of NLP applications, which shows parallel outputs from the NLP model at once to users. Then a decision model is presented that can assist in deciding whether a given condition is suitable to show multiple outputs at once from the NLP model. We hope developers and UX designers can examine the decision model and create an easy-to-use interface that can present numerous results from the NLP model at once. Moreover, we hope future researchers can reference the decision model from this paper to explore the potential of other NLP models’ usage that can show parallel outputs at once to create a more satisfactory user experience.

Publication
Paper published at Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems (CHI EA)
I-Sheng (Eason) Chen
I-Sheng (Eason) Chen
2nd-year PhD Student at Human-Computer Interaction Institute

Eason is a first-year PhD student in HCII at CMU.