Research map / Learning theory and algorithms / Fairness
Comparative Document Summarisation via Classification
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 |
|---|---|---|---|
| Use gradient-based rather than greedy optimization for the mmd-diff objective (ablation) | Comparative news summaries · Automatic evaluation across three news topics, two classifiers, and four prototype sizes | balanced accuracy | Mixed |
| Use gradient-based rather than greedy optimization for mmd-diff (ablation) | Beef Ban summaries · Human article classification | classification accuracy: 7% more accurate | Helped |
| Use the diversity-focused mmd-div objective rather than mmd-diff (ablation) | Comparative news summaries · News datasets, classifiers, and prototype sizes | balanced accuracy | Mixed |
| Use MMD-based comparative objectives rather than existing alternatives | Comparative news summaries · Three news topics, two classifiers, and four prototype sizes | balanced accuracy | Helped |
| Use mmd-critic rather than methods that maintain a fixed number of prototypes per group | USPS digit summaries · USPS | balanced accuracy | Hurt |
| Increase the number of selected prototypes | Comparative summarisation methods · News and USPS | balanced accuracy | Helped |
Closest papers by meaning
- Improving Multi-Document Summarization via Text Classification (AAAI 2017 · similarity 0.84)
- Unsupervised Extractive Summarization with Learnable Length Control Strategies (AAAI 2024 · similarity 0.83)
- PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models (NeurIPS 2024 · similarity 0.82)
- BooookScore: A systematic exploration of book-length summarization in the era of LLMs (ICLR 2024 · similarity 0.82)
- Language Models of Code Are Few-Shot Planners and Reasoners for Multi-Document Summarization with Attribution (AAAI 2025 · similarity 0.81)
- QuerySum: A Multi-Document Query-Focused Summarization Dataset Augmented with Similar Query Clusters (AAAI 2024 · similarity 0.81)
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.