Progress in Machine Learning is often driven by the availability of large datasets, and consistent evaluation metrics for comparing modeling approaches. To this end, we present a repository of conversational datasets consisting of hundreds of millions of examples, and a standardised evaluation procedure for conversational response selection models using '1-of-100 accuracy'. The repository contains scripts that allow researchers to reproduce the standard datasets, or to adapt the pre-processing and data filtering steps to their needs. We introduce and evaluate several competitive baselines for conversational response selection, whose implementations are shared in the repository, as well as a neural encoder model that is trained on the entire training set.
@article{arxiv.1904.06472,
title = {A Repository of Conversational Datasets},
author = {Matthew Henderson and Paweł Budzianowski and Iñigo Casanueva and Sam Coope and Daniela Gerz and Girish Kumar and Nikola Mrkšić and Georgios Spithourakis and Pei-Hao Su and Ivan Vulić and Tsung-Hsien Wen},
journal= {arXiv preprint arXiv:1904.06472},
year = {2019}
}