Research map / Vision-language and multimodal / Human and embodied modeling
M-sense: Modeling Narrative Structure in Short Personal Narratives Using Protagonist’s Mental Representations
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 |
|---|---|---|---|
| integrate protagonist mental-state representations with linguistic features | M-sense on Stories · Stories, climax | F1: 0.578 -> 0.694 | Helped |
| integrate protagonist mental-state representations with linguistic features | M-sense on Stories · Stories, resolution | F1: 0.609 -> 0.743 | Helped |
| fine-tune M-sense on Tripod training data | M-sense · Tripod, TP4 | Mean Annotation Distance (%): 5.23 -> 4.17 | Helped |
| fine-tune M-sense on Tripod training data | M-sense · Tripod, TP5 | Mean Annotation Distance (%): 3.48 -> 2.38 | Helped |
| replace token-level BERT with sentence-level BERT (ablation) | M-sense · Stories validation, climax | F1: 0.688 -> 0.665 | Hurt |
| replace token-level BERT with sentence-level BERT (ablation) | M-sense · Stories validation, resolution | F1: 0.738 -> 0.709 | Hurt |
| replace token-level BERT with sentence-level USE (ablation) | M-sense · Stories validation, climax | F1: 0.688 -> 0.677 | Hurt |
| replace token-level BERT with sentence-level USE (ablation) | M-sense · Stories validation, resolution | F1: 0.738 -> 0.726 | Hurt |
| add a Transformer story encoder (ablation) | M-sense · Stories validation, climax | F1: 0.620 -> 0.688 | Helped |
| add a Transformer story encoder (ablation) | M-sense · Stories validation, resolution | F1: 0.653 -> 0.738 | Helped |
| replace Transformer story encoder with inter-sentence RNN (ablation) | M-sense · Stories validation, climax | F1: 0.688 -> 0.659 | Hurt |
| replace Transformer story encoder with inter-sentence RNN (ablation) | M-sense · Stories validation, resolution | F1: 0.738 -> 0.705 | Hurt |
Closest papers by meaning
- Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind (ICML 2024 · similarity 0.87)
- OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling (NeurIPS 2026 · similarity 0.86)
- Understanding Annotator Perception: Modeling Psychological Inference from First- and Third-Person Annotations (Student Abstract) (AAAI 2025 · similarity 0.84)
- ToMATO: Verbalizing the Mental States of Role-Playing LLMs for Benchmarking Theory of Mind (AAAI 2025 · similarity 0.84)
- SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding (CVPR 2025 · similarity 0.84)
- Human-inspired Episodic Memory for Infinite Context LLMs (ICLR 2025 · similarity 0.83)
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.