Research map / Graph learning / Knowledge and temporal graphs
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks
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 |
|---|---|---|---|
| schema graph with graph attention (SST-2) vs TRADE | multi-domain DST · MultiWOZ 2.1 | joint goal accuracy: 45.6 -> 55.23 | Helped |
| add slot graph relations in RGAT (ablation) | SST-2 · MultiWOZ 2.1 | joint goal accuracy: 52.84 -> 55.23 | Helped |
| add slot graph relations in RGAT (ablation) | SST-2 · MultiWOZ 2.0 | joint goal accuracy: 49.67 -> 51.17 | Helped |
| cross attention between ontology and utterance at every GAMT step (ablation) | SST-2 · MultiWOZ 2.1 | joint goal accuracy: 53.85 -> 55.23 | Helped |
| use more dialogue context (SST-2 vs SST-1) (ablation) | SST · MultiWOZ 2.0 | joint goal accuracy: 47.59 -> 51.17 | Helped |
| SST-3 vs SST-2 (ablation) | SST · MultiWOZ 2.1 | joint goal accuracy: 55.23 -> 54.22 | Hurt |
| more than one RGAT step (ablation) | SST-2 · MultiWOZ 2.0 | joint goal accuracy | Helped |
| classification SST-2 vs generative TRADE on taxi slots | SST-2 · MultiWOZ 2.0 taxi domain | slot accuracy | Hurt |
Closest papers by meaning
- Non-Autoregressive Dialog State Tracking (ICLR 2020 · similarity 0.91)
- Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Tracking (AAAI 2023 · similarity 0.90)
- MA-DST: Multi-Attention-Based Scalable Dialog State Tracking (AAAI 2020 · similarity 0.90)
- Learning to Imagine: Distillation-Based Interactive Context Exploitation for Dialogue State Tracking (AAAI 2023 · similarity 0.88)
- Structure-Aware Multimodal Sequential Learning for Visual Dialog (AAAI 2024 · similarity 0.83)
- StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning (NeurIPS 2026 · 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.