Research map / Architectures and efficiency / Attention and transformers
DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition
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 DialogXL instead of XLNet | XLNet-Base · IEMOCAP | weighted-F1: 61.33 -> 65.94 | Helped |
| use DialogXL instead of XLNet | XLNet-Base · MELD | weighted-F1: 61.65 -> 62.41 | Helped |
| use DialogXL instead of XLNet | XLNet-Base · DailyDialog | micro-F1: 53.62 -> 54.93 | Helped |
| use DialogXL instead of XLNet | XLNet-Base · EmoryNLP | weighted-F1: 34.13 -> 34.73 | Helped |
| add speaker self-attention (ablation) | DialogXL · IEMOCAP | F1 score: 62.30 -> 65.94 (↓3.64) | Helped |
| add speaker self-attention (ablation) | DialogXL · MELD | F1 score: 61.92 -> 62.41 (↓0.49) | Helped |
| add listener self-attention (ablation) | DialogXL · IEMOCAP | F1 score: 62.87 -> 65.94 (↓3.07) | Helped |
| add listener self-attention (ablation) | DialogXL · MELD | F1 score: 62.03 -> 62.41 (↓0.38) | Helped |
| add speaker and listener self-attention (ablation) | DialogXL · IEMOCAP | F1 score: 61.71 -> 65.94 (↓4.23) | Helped |
| add speaker and listener self-attention (ablation) | DialogXL · MELD | F1 score: 61.70 -> 62.41 (↓0.71) | Helped |
| add local self-attention (ablation) | DialogXL · IEMOCAP | F1 score: 61.66 -> 65.94 (↓4.28) | Helped |
| add local self-attention (ablation) | DialogXL · MELD | F1 score: 61.72 -> 62.41 (↓0.69) | Helped |
Closest papers by meaning
- Utterance-level Emotion Recognition in Conversation with Conversation-level Supervision (AAAI 2025 · similarity 0.87)
- Dual-View Learning for Conversational Emotion Recognition Through Context and Emotion-Shift Modeling (AAAI 2025 · similarity 0.87)
- Adaptive Graph Learning for Multimodal Conversational Emotion Detection (AAAI 2024 · similarity 0.86)
- Dynamic Interactive Bimodal Hypergraph Networks for Emotion Recognition in Conversations (AAAI 2025 · similarity 0.85)
- Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding (AAAI 2025 · similarity 0.85)
- SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words (NeurIPS 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.