Research map / Large language models / Language, safety and interpretability
Joint Parsing and Generation for 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 |
|---|---|---|---|
| jointly decode the summary with its dependency structure rather than remove the tree decoder (ablation) | GenParse · Gigaword test | ROUGE-2: 17.10 -> 18.85 | Helped |
| jointly decode the summary with its dependency structure rather than remove the tree decoder (ablation) | GenParse · Newsroom test | ROUGE-1 F: 37.65 -> 41.06 | Helped |
| jointly decode the summary with its dependency structure rather than remove the tree decoder (ablation) | GenParse · CNN/DM-R test | ROUGE-1 F: 46.46 -> 50.49 | Helped |
| jointly decode the summary with its dependency structure rather than remove the tree decoder (ablation) | GenParse · WebMerge test | ROUGE-1 F: 36.23 -> 57.24 | Helped |
| jointly generate summaries and dependency parses | GenParse-Full · WebMerge human evaluation | Q2 meaning preservation accuracy: 38.5 -> 46.8 | Helped |
| jointly generate summaries and dependency parses | GenParse-Full · WebMerge human evaluation | ¬Q3 no additional meanings accuracy: 50.8 -> 53.4 | Helped |
| jointly generate summaries and dependency parses | GenParse-Full · WebMerge human evaluation | grammaticality ranked 2nd: 18.6 -> 42.4 | Helped |
| jointly learn to summarize and parse | GenParse-Full · CNN/DM-R and Newsroom | dependency-relation preservation F-score | Helped |
Closest papers by meaning
- Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees (ICLR 2023 · similarity 0.92)
- Controlling the Amount of Verbatim Copying in Abstractive Summarization (AAAI 2020 · similarity 0.90)
- Faithful to the Original: Fact Aware Neural Abstractive Summarization (AAAI 2018 · similarity 0.90)
- Keywords-Guided Abstractive Sentence Summarization (AAAI 2020 · similarity 0.90)
- Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive Summarization (AAAI 2025 · similarity 0.87)
- Learning from Failure: Improving Meeting Summarization without Good Samples (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.