Research map / Graph learning / Knowledge and temporal graphs
Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms
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 |
|---|---|---|---|
| couple aspect and opinion attentions instead of training independently (ablation) | CMLA · SemEval-15 Restaurant | opinion F1: 72.73 -> 73.68 | Helped |
| couple aspect and opinion attentions instead of training independently (ablation) | CMLA · SemEval-14 Restaurant | aspect F1: 84.14 -> 85.29 | Helped |
| add opinion labels with independent opinion attention (ablation) | ASL · SemEval benchmarks | aspect F1: 84.38 -> 84.14 (S1) | No clear effect |
| use 2 attention layers instead of 1 (ablation) | CMLA · SemEval-15 Restaurant | aspect F1: 69.27 -> 70.73 | Helped |
| use 3 attention layers instead of 2 (ablation) | CMLA · SemEval benchmarks | aspect F1: 85.29 -> 84.41 (S1) | Hurt |
| CMLA without syntactic features instead of RNCRF with dependency parsing | aspect extraction · SemEval-15 Restaurant | aspect F1: 67.06 -> 70.73 | Helped |
| CMLA instead of RNCRF* with hand-crafted features | aspect/opinion extraction · SemEval-14 Laptop | aspect F1: 78.42 -> 77.80 | Hurt |
Closest papers by meaning
- Transferable Interactive Memory Network for Domain Adaptation in Fine-Grained Opinion Extraction (AAAI 2019 · similarity 0.88)
- MNCN: A Multilingual Ngram-Based Convolutional Network for Aspect Category Detection in Online Reviews (AAAI 2019 · similarity 0.87)
- You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification (AAAI 2024 · similarity 0.85)
- Modeling Adaptive Inter-Task Feature Interactions via Sentiment-Aware Contrastive Learning for Joint Aspect-Sentiment Prediction (AAAI 2024 · similarity 0.85)
- Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification (AAAI 2025 · similarity 0.84)
- Harnessing Holistic Discourse Features and Triadic Interaction for Sentiment Quadruple Extraction in Dialogues (AAAI 2024 · similarity 0.84)
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.