Towards making NLG a voice for interpretable Machine Learning

WS 2018 James ForrestSomayajulu SripadaWei PangGeorge Coghill

This paper presents a study to understand the issues related to using NLG to humanise explanations from a popular interpretable machine learning framework called LIME. Our study shows that self-reported rating of NLG explanation was higher than that for a non-NLG explanation... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.