We present an automated evaluation method to measure fluidity in conversational dialogue systems. The method combines various state of the art Natural Language tools into a classifier, and human ratings on these dialogues to train an automated judgment model. Our experiments show that the results are an improvement on existing metrics for measuring fluidity.
@article{arxiv.1910.11790,
title = {Measuring Conversational Fluidity in Automated Dialogue Agents},
author = {Keith Vella and Massimo Poesio and Michael Sigamani and Cihan Dogan and Aimore Dutra and Dimitrios Dimakopoulos and Alfredo Gemma and Ella Walters},
journal= {arXiv preprint arXiv:1910.11790},
year = {2019}
}