Research map / Large language models / Language, safety and interpretability
Generating Character Descriptions for Automatic Summarization of Fiction
Weiwei Zhang, Jackie Chi Kit Cheung, Joel Oren
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use abstractive classifier (attr + relevant + full contexts) instead of SVM baseline | character attribute prediction · Author-annotated character attributes | Recall@4: 0.0505 -> 0.1266 | Improved |
| use abstractive classifier instead of extractive ranking | character attribute prediction · Author-annotated character attributes | Recall@4: 0.0631 -> 0.1266 | Improved |
| add full-context features to extractive ranker (ablation) | extractive GBDT · Author-annotated character attributes | Recall@4: 0.0631 -> 0.0631 | No clear effect |
| add relevant-sentence context to abstractive classifier with attribute only vs combination (ablation) | abstractive classifier · Author-annotated character attributes | Recall@4: 0.1193 -> 0.1266 | Improved |
| add relevant sentence to full contexts (ablation) | abstractive classifier · Author-annotated character attributes | Recall@4: 0.1104 -> 0.1266 | Improved |
| replace full contexts with relevant sentence (ablation) | abstractive classifier · Author-annotated character attributes | Recall@4: 0.1104 -> 0.1193 | Improved |
| abstractive (candidates from corpus list) instead of extractive (story text only) | attribute candidate source · Author-annotated character attributes | Recall@4: 0.0631 -> 0.1193 | Improved |
| use top-1 most similar sentence instead of top-k (ablation) | abstractive classifier · Author-annotated character attributes | validation performance | Improved |
| classification target instead of similarity regression for abstractive model | abstractive classifier · Author-annotated character attributes | label quality | Improved |
Closest papers by meaning
- A Character-Centric Neural Model for Automated Story Generation (AAAI 2020 · similarity 0.86)
- Inferring Interpersonal Relations in Narrative Summaries (AAAI 2016 · similarity 0.84)
- Agents' Room: Narrative Generation through Multi-step Collaboration (ICLR 2025 · similarity 0.82)
- BooookScore: A systematic exploration of book-length summarization in the era of LLMs (ICLR 2024 · similarity 0.81)
- PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models (NeurIPS 2024 · similarity 0.80)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 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.
