We present a novel approach to generating scripts by using agents with different personality types. To manage character interaction in the script, we employ simulated dramatic networks. Automatic and human evaluation on multiple criteria shows that our approach outperforms a vanilla-GPT2-based baseline. We further introduce a new metric to evaluate dialogue consistency based on natural language inference and demonstrate its validity.
@article{arxiv.2206.08425,
title = {DialogueScript: Using Dialogue Agents to Produce a Script},
author = {Patrícia Schmidtová and Dávid Javorský and Christián Mikláš and Tomáš Musil and Rudolf Rosa and Ondřej Dušek},
journal= {arXiv preprint arXiv:2206.08425},
year = {2022}
}
Comments
Non-archival paper at the 4th Workshop on Narrative Understanding (WNU 2022)