Research map / Graph learning / Knowledge and temporal graphs
GraphMemDialog: Optimizing End-to-End Task-Oriented Dialog Systems Using Graph Memory 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 |
|---|---|---|---|
| Use context-aware graph memory with multi-hop reasoning over KB entities | GraphMemDialog · CamRest | Entity F1: 64.4 vs. 62.1 | Helped |
| Use context-aware graph memory with multi-hop reasoning over KB entities | GraphMemDialog · In-Car Assistant | Entity F1: 64.5 vs. 61.1 | Helped |
| Use context-aware graph memory with multi-hop reasoning over KB entities | GraphMemDialog · MultiWOZ 2.1 | Entity F1: 40.2 vs. 36.0 | Helped |
| Add GMN for context-aware KB entity representations and iterative interaction (ablation) | GraphMemDialog · CamRest | Entity F1: 56.2 -> 64.4 | Helped |
| Add GMN for context-aware KB entity representations and iterative interaction (ablation) | GraphMemDialog · In-Car Assistant | Entity F1: 52.0 -> 64.5 | Helped |
| Add GMN for context-aware KB entity representations and iterative interaction (ablation) | GraphMemDialog · MultiWOZ 2.1 | Entity F1: 31.2 -> 40.2 | Helped |
| Add modified GAT to encode dialog-history structure (ablation) | GraphMemDialog · CamRest | BLEU: 21.2 -> 22.3 | Helped |
| Add modified GAT to encode dialog-history structure (ablation) | GraphMemDialog · In-Car Assistant | BLEU: 18.8 -> 18.8 | No clear effect |
| Add modified GAT to encode dialog-history structure (ablation) | GraphMemDialog · MultiWOZ 2.1 | BLEU: 14.2 -> 14.9 | Helped |
| Replace GMN with COMPGCN (ablation) | GraphMemDialog · CamRest | Entity F1: 64.4 vs. 60.7 | Hurt |
| Replace GMN with RGCN (ablation) | GraphMemDialog · In-Car Assistant | Entity F1: 64.5 vs. 63.4 | Hurt |
| Replace GMN with COMPGCN (ablation) | GraphMemDialog · MultiWOZ 2.1 | Entity F1: 40.2 vs. 40.3 | Mixed |
Closest papers by meaning
- Iterative Context-Aware Graph Inference for Visual Dialog (CVPR 2020 · similarity 0.91)
- Structure-Aware Multimodal Sequential Learning for Visual Dialog (AAAI 2024 · similarity 0.89)
- From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs (ICLR 2025 · similarity 0.88)
- PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents (ICML 2026 · similarity 0.87)
- TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling (AAAI 2024 · similarity 0.86)
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025 · similarity 0.86)
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.