Research map / Label-efficient and robust learning / Recognition and long-tail
Weakly-Supervised Opinion Summarization by Leveraging External Information
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 five trainable memory cells for the General aspect (ablation) | AspMem · OpoSum aspect identification | multi-class F1: 54.2 -> 60.2 | Helped |
| Use AspMem instead of MATE | OpoSum aspect identification · OpoSum aspect identification | multi-class F1: 49.1 -> 54.2 | Helped |
| Remove redundancy filtering (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-1: 46.6 -> 48.0 | Helped |
| Remove redundancy filtering (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-2: 25.7 -> 28.7 | Helped |
| Add the aspect-relevance score (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-1: 41.5 -> 46.6 | Helped |
| Add the aspect-relevance score (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-2: 20.5 -> 25.7 | Helped |
| Add the sentiment score (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-1: 40.5 -> 46.6 | Helped |
| Add the sentiment score (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-2: 18.2 -> 25.7 | Helped |
| Use ILP selection instead of greedy selection (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-1: 46.2 -> 46.6 | Helped |
| Use ILP selection instead of greedy selection (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-2: 25.1 -> 25.7 | Helped |
| Replace external feature-description seed-words with MATE's review-derived seed-words (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-1: 46.6 -> 45.6 | Hurt |
| Replace external feature-description seed-words with MATE's review-derived seed-words (ablation) | AspMemSum · OpoSum opinion summarization | ROUGE-2: 25.7 -> 24.5 | Hurt |
Closest papers by meaning
- Unsupervised Opinion Summarization with Content Planning (AAAI 2021 · similarity 0.89)
- Microsummarization of Online Reviews: An Experimental Study (AAAI 2016 · similarity 0.86)
- Transferable Interactive Memory Network for Domain Adaptation in Fine-Grained Opinion Extraction (AAAI 2019 · similarity 0.86)
- MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization (ICML 2019 · similarity 0.86)
- PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models (NeurIPS 2024 · similarity 0.83)
- Tell Me What Is Good about This Property: Leveraging Reviews for Segment-Personalized Image Collection Summarization (AAAI 2024 · similarity 0.82)
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.