Datasets › MENSA
MENSA (Movie Scene Saliency Dataset)
MENSA: Movie Scene Saliency Dataset
Dataset Summary
The dataset, MENSA (Movie Scene Saliency Dataset) is from the paper "Select and Summarize: Scene Saliency for Movie Script Summarization", and consists of movie scripts and their corresponding summaries. Each scene in the movie script is annotated with scene saliency labels. The training set contains silver labels, which are automatically generated, while the validation and test sets contain human-annotated gold labels.
Dataset Structure
The dataset is divided into three parts: - Training Set: Contains movie scripts and summaries with silver scene saliency labels. - Validation Set: Contains movie scripts and summaries with human-annotated gold scene saliency labels. - Test Set: Contains movie scripts and summaries with human-annotated gold scene saliency labels.
Benchmarks archive 2025-07-28
All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Long-Form Narrative Summarization | MENSA | NexusSum (Mistral Large) BERTScore (F1) 65.73 | NexusSum: Hierarchical LLM Agents for Long-Form... | — | 10 | Compare |
Papers archive 2025-07-28
4 shown of 4 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 4. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization | 0 | 2 | 30 May 2025 | not harvested |
| Agent-as-Judge for Factual Summarization of Long Narratives | 1 | 1 | 17 Jan 2025 | ran 0 of 13 samples (13 unverified) |
| End-to-End Long Document Summarization using Gradient Caching | 0 | 4 | 3 Jan 2025 | not harvested |
| Select and Summarize: Scene Saliency for Movie Script Summarization | 1 | 3 | 4 Apr 2024 | not harvested |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
No modality tagged.
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- MENSA
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections