English

Measuring Conversational Fluidity in Automated Dialogue Agents

Computation and Language 2019-10-28 v1

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T11:55:05.587Z