Research map / Label-efficient and robust learning / Recognition and long-tail
Unsupervised Learning of Evolving Relationships Between Literary Characters
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add global component to GHMM with penalty (Globally Aware GHMM) (ablation) | GHMM · binary relationship alignment | F-measure | Helped |
| add transition penalty to GHMM (ablation) | GHMM · binary relationship alignment | F-measure | No clear effect |
| add transition penalty to Globally Aware GHMM (ablation) | Globally Aware GHMM · binary relationship alignment | F-measure | Helped |
| add local Markov structure to the global-only clustering model (ablation) | Global Model · binary relationship alignment | F-measure | Helped |
| use Globally Aware GHMM instead of RMN | relationship sequence quality · human preference, 133 pairs | fraction preferring model: 66.2% chosen | Helped |
| use Globally Aware GHMM instead of RMN | state quality · states judged as relationships | percent judged relationship: 50.0% -> 66.0% | Helped |
| estimate covariance matrix instead of fixed diagonal (ablation) | GHMM models · binary relationship alignment | performance | Hurt |
Closest papers by meaning
- Modeling Evolving Relationships Between Characters in Literary Novels (AAAI 2016 · similarity 0.94)
- Inferring Interpersonal Relations in Narrative Summaries (AAAI 2016 · similarity 0.89)
- M-sense: Modeling Narrative Structure in Short Personal Narratives Using Protagonist’s Mental Representations (AAAI 2023 · similarity 0.86)
- Correlation Dimension of Autoregressive Large Language Models (NeurIPS 2025 · similarity 0.83)
- Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework (AAAI 2023 · similarity 0.83)
- OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling (NeurIPS 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.