Research map / Graph learning / Graph self-supervised learning
Graph LSTM with Context-Gated Mechanism for Spoken Language Understanding
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 ELMo embeddings instead of non-pretrained word embeddings (ablation) | Graph LSTM · Snips | slot F1: 93.81 -> 95.30 | Helped |
| use ELMo embeddings (ablation) | Graph LSTM · ATIS | slot F1: 95.84 -> 95.91 | Helped |
| add context gate (conv + self-attention) (ablation) | Graph LSTM · Snips | slot F1: 94.56 -> 95.30 | Helped |
| add context gate (ablation) | Graph LSTM · ATIS | slot F1: 95.72 -> 95.91 | Helped |
| add context gate (ablation) | Graph LSTM · Snips | sentence accuracy: 88.00 -> 89.71 | Helped |
| add context gate (ablation) | Graph LSTM · ATIS | intent accuracy: 97.09 -> 97.20 | No clear effect |
| train slot filling and intent detection jointly instead of slot only (ablation) | Graph LSTM · Snips | slot F1: 94.28 -> 95.30 | Helped |
| train jointly instead of intent only (ablation) | Graph LSTM · Snips | intent accuracy: 97.71 -> 98.29 | Helped |
| train jointly instead of slot only (ablation) | Graph LSTM · ATIS | slot F1: 95.79 -> 95.91 | Helped |
| train jointly instead of intent only (ablation) | Graph LSTM · ATIS | intent accuracy: 96.64 -> 97.20 | Helped |
| add named entity features | Graph LSTM · ATIS | slot F1: 95.91 -> 97.28 | Helped |
| use Graph LSTM instead of SF-ID Network | SLU model · ATIS | intent accuracy: 97.76 -> 97.20 | Mixed |
Closest papers by meaning
- Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction (AAAI 2024 · similarity 0.87)
- Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding (AAAI 2026 · similarity 0.87)
- Towards Multi-Intent Spoken Language Understanding via Hierarchical Attention and Optimal Transport (AAAI 2024 · similarity 0.86)
- Aligner²: Enhancing Joint Multiple Intent Detection and Slot Filling via Adjustive and Forced Cross-Task Alignment (AAAI 2024 · similarity 0.85)
- MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark (ICLR 2026 · similarity 0.84)
- Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data (ICML 2025 · 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.