Research map / Graph learning / Graph self-supervised learning
Co-Guiding for Multi-Intent Spoken Language Understanding
Bowen Xing, Ivor Wai-Hung Tsang
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 slot-to-intent guidance (ablation) | Co-guiding Net · MixATIS | Overall accuracy: 47.4 -> 50.9 | Improved |
| add slot-to-intent guidance (ablation) | Co-guiding Net · MixSNIPS | Overall accuracy: 76.3 -> 77.2 | Improved |
| add intent-to-slot guidance (ablation) | Co-guiding Net · MixATIS | Overall accuracy: 47.3 -> 50.9 | Improved |
| add intent-to-slot guidance (ablation) | Co-guiding Net · MixSNIPS | Overall accuracy: 76.2 -> 77.2 | Improved |
| add relations on heterogeneous semantics-label graphs (ablation) | Co-guiding Net · MixATIS | Overall accuracy: 45.6 -> 50.9 | Improved |
| add relations on heterogeneous semantics-label graphs (ablation) | Co-guiding Net · MixSNIPS | Overall accuracy: 76.0 -> 77.2 | Improved |
| add Local Slot-aware GAT (ablation) | Co-guiding Net · MixATIS | Overall accuracy: 50.9 -> 50.7 | Hurt |
| add Local Slot-aware GAT (ablation) | Co-guiding Net · MixSNIPS | Overall accuracy: 77.2 -> 75.6 | Hurt |
| add single-task supervised contrastive learning (ablation) | BERT+Co-guiding-SCL Net · MixATIS | Overall accuracy | Improved |
| add co-guiding supervised contrastive learning (ablation) | BERT+Co-guiding-SCL Net · MixATIS | Overall accuracy | Improved |
| add supervised contrastive learning on top of Co-guiding Net (LSTM) | Co-guiding Net · MixATIS | Overall accuracy: 50.9 -> 51.9 | Improved |
| add supervised contrastive learning on top of Co-guiding Net (XLNet) | Co-guiding Net · MixATIS | Overall accuracy: 54.0 -> 56.7 | Improved |
Closest papers by meaning
- Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction (AAAI 2024 · similarity 0.90)
- Towards Multi-Intent Spoken Language Understanding via Hierarchical Attention and Optimal Transport (AAAI 2024 · similarity 0.90)
- Aligner²: Enhancing Joint Multiple Intent Detection and Slot Filling via Adjustive and Forced Cross-Task Alignment (AAAI 2024 · similarity 0.88)
- Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding (AAAI 2026 · similarity 0.85)
- Divide-Solve-Combine: An Interpretable and Accurate Prompting Framework for Zero-shot Multi-Intent Detection (AAAI 2025 · similarity 0.85)
- MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations (ICLR 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.
