Research map / Architectures and efficiency / RNNs and normalization
End-to-End Trainable Non-Collaborative Dialog System
Yu Li, Kun Qian, Weiyan Shi, Zhou Yu
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 response filtering (ablation) | MISSA · AntiScam | engagement (human): 2.87 -> 3.69 | Improved |
| add response filtering (ablation) | MISSA · AntiScam | perplexity: 30.54 -> 21.07 | Improved |
| condition generation on system intent token (ablation) | MISSA · AntiScam | fluency (human): 3.78 -> 4.18 | Improved |
| condition generation on system intent token (ablation) | MISSA · AntiScam | coherence (human): 3.68 -> 3.75 | Improved |
| condition generation on system intent token (ablation) | MISSA · AntiScam | engagement and task success: 3.78 -> 3.69 engagement; 1.341 -> 1.294 task success | Mixed |
| condition generation on system intent token (ablation) | MISSA · PersuasionForGood | ERIP: 52.6 -> 51.6 | Hurt |
| add intent and slot classifiers with conditional generation (MISSA vs TransferTransfo) | TransferTransfo · AntiScam | dialog length: 8.5 -> 14.9 | Improved |
| add intent and slot classifiers with conditional generation (MISSA vs TransferTransfo) | TransferTransfo · AntiScam | task success score: 1.025 -> 1.294 | Improved |
| MISSA vs Hybrid on-task/off-task switching | Hybrid · AntiScam | coherence (human): 2.76 -> 3.75 | Improved |
| add intent and slot classifiers (MISSA vs TransferTransfo) | TransferTransfo · AntiScam | ERIP: 48.0% -> 47.2% | Mixed |
| add response filtering (ablation) | MISSA · PersuasionForGood | ERIP: 48.9% -> 51.6% | Improved |
Closest papers by meaning
- Learning End-to-End Goal-Oriented Dialog (ICLR 2017 · similarity 0.88)
- TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling (AAAI 2024 · similarity 0.88)
- Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History (ICLR 2020 · similarity 0.87)
- Task-Oriented Dialog Systems That Consider Multiple Appropriate Responses under the Same Context (AAAI 2020 · similarity 0.86)
- Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action (NeurIPS 2026 · similarity 0.86)
- Cooper: Coordinating Specialized Agents towards a Complex Dialogue Goal (AAAI 2024 · similarity 0.85)
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.
