Research map / Graph learning / Knowledge and temporal graphs
Inferring Interpersonal Relations in Narrative Summaries
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 structural triad features to text-based relation classification | SPR · Movie summaries test set | accuracy: 0.701 -> 0.792 | Helped |
| Add narrative-specific clustering (K=2) | SPR · Movie summaries test set | accuracy: 0.792 -> 0.804 | Helped |
| Add joint participation in actions (Are Team features) (ablation) | Text-based relation classifier · Movie summaries cross-validation | cooperative-class precision and recall | Helped |
| Add Are Team features (ablation) | Text-based relation classifier · Movie summaries cross-validation | non-cooperative-class recall | No clear effect |
| Add frame-semantic features (ablation) | Text-based relation classifier · Movie summaries cross-validation | model performance | No clear effect |
| Add adverbial connotations of character actions (ablation) | Text-based relation classifier · Movie summaries cross-validation | model performance | No clear effect |
| Remove sentiment and connotation features from surrogate action features (ablation) | Text-based relation classifier · Movie summaries cross-validation | model performance | Hurt |
| Add sentiment and connotation features for actions in SVO roles (Acts Together) (ablation) | Text-based relation classifier · Movie summaries cross-validation | model performance | Helped |
| Add span-based lexical sentiment features (ablation) | Text-based relation classifier · Movie summaries cross-validation | model performance | Helped |
Closest papers by meaning
- Unsupervised Learning of Evolving Relationships Between Literary Characters (AAAI 2017 · similarity 0.89)
- MultiSum: A Multi-Facet Approach for Extractive Social Summarization Utilizing Semantic and Sociological Relationships (AAAI 2024 · similarity 0.82)
- OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling (NeurIPS 2026 · similarity 0.81)
- PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models (NeurIPS 2024 · similarity 0.81)
- Evaluating Whether LLMs Can Reliably Connect the DOTs? (NeurIPS 2026 · similarity 0.81)
- Learning from Failure: Improving Meeting Summarization without Good Samples (AAAI 2024 · similarity 0.80)
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.