Telling Stories through Multi-User Dialogue by Modeling Character Relations
Si, Wai Man, Ammanabrolu, Prithviraj, Riedl, Mark O.
–arXiv.org Artificial Intelligence
This paper explores character-driven story continuation, in which the story emerges through characters' first- and second-person narration as well as dialogue -- requiring models to select language that is consistent with a character's persona and their relationships with other characters while following and advancing the story. We hypothesize that a multi-task model that trains on character dialogue plus character relationship information improves transformer-based story continuation. To this end, we extend the Critical Role Dungeons and Dragons Dataset (Rameshkumar and Bailey, 2020) -- consisting of dialogue transcripts of people collaboratively telling a story while playing the role-playing game Dungeons and Dragons -- with automatically extracted relationships between each pair of interacting characters as well as their personas. A series of ablations lend evidence to our hypothesis, showing that our multi-task model using character relationships improves story continuation accuracy over strong baselines.
arXiv.org Artificial Intelligence
May-31-2021
- Country:
- Oceania > Australia
- North America > United States
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > Los Angeles County
- Long Beach (0.04)
- Minnesota > Hennepin County
- Europe
- Germany > Saarland
- Saarbrücken (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Germany > Saarland
- Genre:
- Research Report (0.40)
- Industry:
- Leisure & Entertainment > Games > Computer Games (0.34)
- Technology: