Research map / Vision-language and multimodal / Human and embodied modeling
Abstractive Text Summarization by Incorporating Reader Comments
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 reader attention to the decoder attention distribution | S2S · Weibo summarization | ROUGE-1: 23.86 -> 24.70 | Helped |
| Add comment denoising module (ablation) | RASG · Weibo summarization | ROUGE-L: 24.64 -> 27.16 | Helped |
| Add gap content to the generator (ablation) | RASG · Weibo summarization | ROUGE-L: 25.28 -> 27.16 | Helped |
| Add the goal tracker (ablation) | RASG · Weibo summarization | ROUGE-1: 22.75 -> 30.33 | Helped |
| Add the discriminator and its feature guidance to the goal tracker (ablation) | RASG w/o GTD · Weibo summarization | ROUGE-L: 17.70 -> 20.80 | Helped |
Closest papers by meaning
- Exploring Human-Like Reading Strategy for Abstractive Text Summarization (AAAI 2019 · similarity 0.89)
- MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization (ICML 2019 · similarity 0.89)
- A Deep Reinforced Model for Abstractive Summarization (ICLR 2018 · similarity 0.88)
- SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents (AAAI 2017 · similarity 0.88)
- Faithful to the Original: Fact Aware Neural Abstractive Summarization (AAAI 2018 · similarity 0.88)
- Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization (ICLR 2026 · similarity 0.87)
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.