We study conversational dialog in which there are many possible responses to a given history. We present the MultiTalk Dataset, a corpus of over 320,000 sentences of written conversational dialog that balances a high branching factor (10) with several conversation turns (6) through selective branch continuation. We make multiple contributions to study dialog generation in the highly branching setting. In order to evaluate a diverse set of generations, we propose a simple scoring algorithm, based on bipartite graph matching, to optimally incorporate a set of diverse references. We study multiple language generation tasks at different levels of predictive conversation depth, using textual attributes induced automatically from pretrained classifiers. Our culminating task is a challenging theory of mind problem, a controllable generation task which requires reasoning about the expected reaction of the listener.
@article{arxiv.2102.01263,
title = {MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations},
author = {Yao Dou and Maxwell Forbes and Ari Holtzman and Yejin Choi},
journal= {arXiv preprint arXiv:2102.01263},
year = {2021}
}