Generating Stylistic and Personalized Dialogues for Virtual Agents in Narratives
Authors: Xu, W., Charles, F., Hargood, C.
Journal: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems Aamas
Publication Date: 01/01/2023
Volume: 2023-May
Pages: 737-746
eISSN: 1558-2914
ISSN: 1548-8403
Abstract:Virtual agents interact with each other through dialogues in various types of narratives (e.g. films). In this paper, we propose an approach on the basis of DialoGPT pre-trained language model, which explores the impact of dialogue generation with different levels of agents' personalities derived from narrative films based on the Big-Five model, as well as with three different embedding methods. From the experimental results using automatic metrics and human user evaluation, we investigate and analyze the impact of different settings on narrative dialogue generation. We demonstrate that our approach is able to generate dialogues with increased variety that correctly reflect the corresponding target personality.
https://eprints.bournemouth.ac.uk/38054/
Source: Scopus
Generating Stylistic and Personalized Dialogues for Virtual Agents in Narratives
Authors: Xu, W., Charles, F., Hargood, C.
Conference: The 22nd International Conference on Autonomous Agents and Multiagent Systems
Dates: 29/05/2023
Journal: IFAAMAS
Publication Date: 29/05/2023
DOI: 10.5555/3545946.3598706
Abstract:Virtual agents interact with each other through dialogues in various types of narratives (e.g. narrative films). In this paper, we propose an approach on the basis of DialoGPT pre-trained language model, which explores the impact of dialogue generation with different levels of agents’ personalities derived from narrative films based on Big-Five model, as well as with three different embedding methods.
From the experimental results using automatic metrics and human judgments, we investigate and analyze the impact of different settings on narrative dialogue generation. Also, we demonstrate that our approach is able to generate dialogues with increased variety that correctly reflect the corresponding target personality.
https://eprints.bournemouth.ac.uk/38054/
Source: Manual