Research map / Label-efficient and robust learning / Recognition and long-tail
STAGE: Span Tagging and Greedy Inference Scheme for Aspect Sentiment Triplet Extraction
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 |
|---|---|---|---|
| Use STAGE span tagging and greedy inference instead of the strongest listed baseline | BERT-base-uncased ASTE model · 14lap | F1: 59.58 -> 61.58 | Helped |
| Use STAGE span tagging and greedy inference instead of the strongest listed baseline | BERT-base-uncased ASTE model · 14res | F1: 71.58 -> 73.76 | Helped |
| Use STAGE span tagging and greedy inference instead of the strongest listed baseline | BERT-base-uncased ASTE model · 15res | F1: 63.05 -> 64.79 | Helped |
| Use STAGE span tagging and greedy inference instead of the strongest listed baseline | BERT-base-uncased ASTE model · 16res | F1: 70.29 -> 73.24 | Helped |
| Add separate aspect, opinion, and sentiment-snippet role dimensions rather than projecting all roles into one (ablation) | STAGE ASTE model · 14lap | F1: 61.49 -> 61.58 | No clear effect |
| Add a separate aspect-opinion role dimension rather than projecting aspect and opinion into one (ablation) | STAGE ASTE model · 14lap | F1: 61.88 -> 61.58 | Hurt |
| Add separate aspect, opinion, and sentiment-snippet role dimensions rather than projecting all roles into one (ablation) | STAGE ASTE model · 14res | F1: 73.58 -> 73.76 | Helped |
| Add a separate aspect-opinion role dimension rather than projecting aspect and opinion into one (ablation) | STAGE ASTE model · 14res | F1: 73.61 -> 73.76 | Helped |
| Add separate aspect, opinion, and sentiment-snippet role dimensions rather than projecting all roles into one (ablation) | STAGE ASTE model · 15res | F1: 64.37 -> 64.79 | Helped |
| Add a separate aspect-opinion role dimension rather than projecting aspect and opinion into one (ablation) | STAGE ASTE model · 15res | F1: 64.94 -> 64.79 | Hurt |
| Add separate aspect, opinion, and sentiment-snippet role dimensions rather than projecting all roles into one (ablation) | STAGE ASTE model · 16res | F1: 73.45 -> 73.24 | Hurt |
| Add a separate aspect-opinion role dimension rather than projecting aspect and opinion into one (ablation) | STAGE ASTE model · 16res | F1: 72.75 -> 73.24 | Helped |
Closest papers by meaning
- Aspect Enhancement and Text Simplification in Multimodal Aspect-Based Sentiment Analysis for Multi-Aspect and Multi-Sentiment Scenarios (AAAI 2025 · similarity 0.86)
- Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations (AAAI 2024 · similarity 0.86)
- TextGT: A Double-View Graph Transformer on Text for Aspect-Based Sentiment Analysis (AAAI 2024 · similarity 0.86)
- A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis (AAAI 2024 · similarity 0.85)
- SimRP: Syntactic and Semantic Similarity Retrieval Prompting Enhances Aspect Sentiment Quad Prediction (AAAI 2025 · similarity 0.85)
- You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification (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.