Research map / Label-efficient and robust learning / Recognition and long-tail
Improving Opinion Aspect Extraction Using Semantic Similarity and Aspect Associations
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 similarity + association recommendation (AER) over DP | DP · Hu&Liu D1-D5 avg (multiple occurrences) | F1: 79.1 -> 87.0 | Helped |
| add similarity + association recommendation (AER) over DP | DP · Liu2015 D6-D8 avg (distinct terms) | F1: 67.9 -> 73.3 | Helped |
| add association recommendation to similarity-only (SimR -> AER) (ablation) | AER · Hu&Liu D1-D5 avg (distinct terms) | F1: 72.8 -> 75.9 | Helped |
| add similarity recommendation to association-only (ARR -> AER) (ablation) | AER · Hu&Liu D1-D5 avg (distinct terms) | F1: 60.1 -> 75.9 | Helped |
| word-vector similarity recommendation on DP- base (SimR) (ablation) | DP- · Hu&Liu D1-D5 avg (multiple occurrences) | F1: 72.6 -> 85.0 | Helped |
| association recommendation on DP- base (ARR) (ablation) | DP- · Hu&Liu D1-D5 avg (multiple occurrences) | F1: 72.6 -> 80.4 | Helped |
| add more dependency relations to rules (DP -> DP+) | DP · Hu&Liu D1-D5 avg (multiple occurrences) | F1: 79.1 -> 76.4 | Hurt |
| keep only high-precision rules (DP -> DP-) | DP · Hu&Liu D1-D5 avg (multiple occurrences) | F1: 79.1 -> 72.6 | Hurt |
| word vectors instead of WordNet similarity (SYN, WUP, LIN, PATH) (ablation) | SimR · D1-D8 avg | F1 | Helped |
| mine association rules from 100 domains instead of 50 electronic domains (ablation) | AER · D1-D8 avg | F1 | Helped |
Closest papers by meaning
- Transferable Interactive Memory Network for Domain Adaptation in Fine-Grained Opinion Extraction (AAAI 2019 · similarity 0.87)
- Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations (AAAI 2024 · similarity 0.83)
- You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification (AAAI 2024 · similarity 0.81)
- Modeling Adaptive Inter-Task Feature Interactions via Sentiment-Aware Contrastive Learning for Joint Aspect-Sentiment Prediction (AAAI 2024 · similarity 0.81)
- Aspect Enhancement and Text Simplification in Multimodal Aspect-Based Sentiment Analysis for Multi-Aspect and Multi-Sentiment Scenarios (AAAI 2025 · similarity 0.81)
- DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis (AAAI 2026 · 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.