all AI news
Which Factors Predict the Chat Experience of a Natural Language Generation Dialogue Service?. (arXiv:2304.10785v1 [cs.CL])
cs.CL updates on arXiv.org arxiv.org
In this paper, we proposed a conceptual model to predict the chat experience
in a natural language generation dialog system. We evaluated the model with 120
participants with Partial Least Squares Structural Equation Modeling (PLS-SEM)
and obtained an R-square (R2) with 0.541. The model considers various factors,
including the prompts used for generation; coherence, sentiment, and similarity
in the conversation; and users' perceived dialog agents' favorability. We then
further explore the effectiveness of the subset of our proposed model. The …
agents arxiv chat conversation dialogue equation experience language language generation least modeling natural natural language natural language generation paper r-square sem sentiment service squares