Research map / Architectures and efficiency / RNNs and normalization
Learning End-to-End Goal-Oriented Dialog
Antoine Bordes, Y-Lan Boureau, Jason Weston
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 match type features (ablation) | Memory Network · T4: Providing information | per-response accuracy: 59.5 -> 100 | Improved |
| Add match type features (ablation) | Memory Network · T1 OOV: Issuing API calls | per-response accuracy: 72.3 -> 96.5 | Improved |
| Add match type features (ablation) | Memory Network · T2 OOV: Updating API calls | per-response accuracy: 78.9 -> 94.5 | Improved |
| Add match type features (ablation) | Memory Network · T4 OOV: Providing information | per-response accuracy: 57.6 -> 100 | Improved |
| Add match type features (ablation) | Memory Network · T5: Full dialogs | per-response accuracy: 96.1 -> 93.4 | Hurt |
| Add match type features (ablation) | Memory Network · T2: Updating API calls | per-response accuracy: 100 -> 98.3 | Hurt |
| Add match type features (ablation) | Memory Network · T3: Displaying options | per-response accuracy: 74.9 -> 74.9 | No clear effect |
| Add match type features (ablation) | Memory Network · DSTC2 (T6) | per-response accuracy: 41.1 -> 41.0 | No clear effect |
| Use 2 hops rather than 1 (ablation) | Memory Network on T3 · T3: Displaying options | per-response accuracy: 64.8 -> 74.7 | Improved |
| Use MemNN rather than the rule-based baseline | DSTC2 (T6) · DSTC2 (T6) | per-response accuracy: 33.3 -> 41.1 | Improved |
| Use Memory Network rather than supervised embeddings | Concierge · Concierge | per-response accuracy: 14.6 -> 16.7 | Improved |
Closest papers by meaning
- End-to-End Trainable Non-Collaborative Dialog System (AAAI 2020 · similarity 0.88)
- 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 0.85)
- An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems (ICML 2024 · similarity 0.85)
- MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents (AAAI 2026 · similarity 0.84)
- Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics (ICLR 2025 · 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.
