Research map / Label-efficient and robust learning / Recognition and long-tail
From Independent Prediction to Reordered Prediction: Integrating Relative Position and Global Label Information to Emotion Cause Identification
Zixiang Ding, Huihui He, Mengran Zhang, Rui Xia
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 relative position augmented embedding learning to Bi-LSTM (ablation) | Bi-LSTM · Chinese emotion cause corpus | F-measure | Improved |
| add relative position augmented embedding learning to Bi-LSTM (ablation) | Bi-LSTM · Chinese emotion cause corpus | recall | Improved |
| add dynamic global labels to PAE (ablation) | PAE · Chinese emotion cause corpus | F-measure: 4.06% | Improved |
| learn position by encode-decode-style relative-position supervision rather than appending position as a word (ablation) | Bi-LSTM position modeling · Chinese emotion cause corpus | F-measure | Improved |
| learn position by encode-decode-style relative-position supervision rather than concatenating position at clause level (ablation) | Bi-LSTM position modeling · Chinese emotion cause corpus | F-measure | Improved |
| reorder clauses by distance from the emotion clause instead of retaining document order (ablation) | PAE-DGL · Chinese emotion cause corpus | F-measure: 4.78% | Improved |
| use true test labels rather than predicted labels for the dynamic global label feature (ablation) | DGL · Chinese emotion cause corpus | F-measure: 5.04% | Improved |
| use PAE-DGL instead of ConvMS-Memnet | emotion cause identification · Chinese emotion cause corpus | F-measure: 2.87% | Improved |
| use PAE-DGL instead of the best prior precision result | emotion cause identification · Chinese emotion cause corpus | precision: 5.43% | Improved |
Closest papers by meaning
- Learning Emotion Category Representation to Detect Emotion Relations Across Languages (TPAMI 2025 · similarity 0.85)
- EmoGrowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation Graph (ICML 2025 · similarity 0.83)
- AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition (NeurIPS 2026 · similarity 0.83)
- OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition (ICML 2025 · similarity 0.82)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.82)
- A Unified and Interpretable Emotion Representation and Expression Generation (CVPR 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.
