Research map / Image generation / Text-to-image diffusion
Faithful to the Original: Fact Aware Neural Abstractive Summarization
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 extracted fact descriptions as an additional input to the attentional s2s model (ablation) | FTSum_g · Gigaword test | ROUGE-2 F1: 15.52 -> 17.65 | Helped |
| Add gated selection between sentence and fact context instead of concatenating the contexts (ablation) | FTSum · Gigaword test | ROUGE-2 F1: 16.02 -> 17.65 | Helped |
| Add fact descriptions and dual attention to the standard attentional s2s model | Gigaword summarization · Gigaword test (100 manually assessed) | FAKE count: 27 -> 6 | Helped |
Closest papers by meaning
- Controlling the Amount of Verbatim Copying in Abstractive Summarization (AAAI 2020 · similarity 0.90)
- Towards Improving Faithfulness in Abstractive Summarization (NeurIPS 2022 · similarity 0.90)
- Joint Parsing and Generation for Abstractive Summarization (AAAI 2020 · similarity 0.90)
- Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees (ICLR 2023 · similarity 0.88)
- Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive Summarization (AAAI 2025 · similarity 0.85)
- Improving Faithfulness in Abstractive Text Summarization with EDUs Using BART (Student Abstract) (AAAI 2024 · similarity 0.85)
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.