Research map / Label-efficient and robust learning / Recognition and long-tail
DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification
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 |
|---|---|---|---|
| Explicitly model cross-task information with a co-attention relation layer rather than implicit parameter sharing | DCR-Net · Mastodon | SC F1 (%): 39.4 -> 45.1 | Helped |
| Explicitly model cross-task information with a co-attention relation layer rather than implicit parameter sharing | DCR-Net · Mastodon | DAR F1 (%): 54.3 -> 58.6 | Helped |
| Explicitly model cross-task information with a co-attention relation layer rather than implicit parameter sharing | DCR-Net · Dailydialog | SC F1 (%): 33.0 -> 45.4 | Helped |
| Explicitly model cross-task information with a co-attention relation layer rather than implicit parameter sharing | DCR-Net · Dailydialog | DAR F1 (%): 75.7 -> 79.1 | Helped |
| Add the relation layer for explicit interaction between tasks (ablation) | DCR-Net · Mastodon | SC F1 (%): 40.3 -> 45.1 | Helped |
| Add the relation layer for explicit interaction between tasks (ablation) | DCR-Net · Mastodon | DAR F1 (%): 55.2 -> 58.6 | Helped |
| Add the relation layer for explicit interaction between tasks (ablation) | DCR-Net · Dailydialog | SC F1 (%): 38.0 -> 45.4 | Helped |
| Add the relation layer for explicit interaction between tasks (ablation) | DCR-Net · Dailydialog | DAR F1 (%): 78.4 -> 79.1 | Helped |
| Stack multiple relation layers instead of using one (ablation) | DCR-Net · Mastodon | SC F1 (%): 42.5 -> 45.1 | Helped |
| Stack multiple relation layers instead of using one (ablation) | DCR-Net · Dailydialog | SC F1 (%): 42.1 -> 45.4 | Helped |
| Add utterance-level self-attention to capture dialog context (ablation) | DCR-Net · Mastodon | SC F1 (%): 43.2 -> 45.1 | Helped |
| Add utterance-level self-attention to capture dialog context (ablation) | DCR-Net · Dailydialog | DAR F1 (%): 77.2 -> 79.1 | Helped |
Closest papers by meaning
- Dynamic Interactive Bimodal Hypergraph Networks for Emotion Recognition in Conversations (AAAI 2025 · similarity 0.84)
- Winnie: Task-Oriented Dialog System with Structure-Aware Contrastive Learning and Enhanced Policy Planning (AAAI 2024 · similarity 0.83)
- Structure-Aware Multimodal Sequential Learning for Visual Dialog (AAAI 2024 · similarity 0.83)
- TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling (AAAI 2024 · similarity 0.83)
- An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems (ICML 2024 · similarity 0.83)
- MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations (ICLR 2024 · similarity 0.83)
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.