Research map / Label-efficient and robust learning / Domain adaptation and generalization
A Student-Teacher Architecture for Dialog Domain Adaptation Under the Meta-Learning Setting
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 |
|---|---|---|---|
| Add meta-teacher token-loss weighting during adaptation | DAMD trained with MAML · MultiWOZ average | Inform rate: 54.1 -> 58.0 | Helped |
| Add meta-teacher token-loss weighting during adaptation | DAMD trained with MAML · MultiWOZ average | Success rate: 35.5 -> 40.3 | Helped |
| Add meta-teacher token-loss weighting during adaptation | DAMD trained with MAML · MultiWOZ average | BLEU: 7.6 -> 8.2 | Helped |
| Add meta-teacher token-loss weighting during adaptation | DAMD trained with MAML · Schema-Guided Dataset average | Inform rate: 69.2 -> 89.6 | Helped |
| Add meta-teacher token-loss weighting during adaptation | DAMD trained with MAML · Schema-Guided Dataset average | BLEU: 12.0 -> 12.1 | Helped |
| Use meta-teacher token-loss weighting instead of unweighted token loss | DAMD student · MultiWOZ four-domain adaptation | BLEU: 9.49 vs 10.58 at 80 dialogs; 11.97 vs 15.24 at 1600 dialogs | Mixed |
Closest papers by meaning
- MTSS: Learn from Multiple Domain Teachers and Become a Multi-Domain Dialogue Expert (AAAI 2020 · similarity 0.88)
- Exploring Auxiliary Reasoning Tasks for Task-oriented Dialog Systems with Meta Cooperative Learning (AAAI 2021 · similarity 0.88)
- An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems (ICML 2024 · similarity 0.86)
- Structure-Aware Multimodal Sequential Learning for Visual Dialog (AAAI 2024 · similarity 0.86)
- TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling (AAAI 2024 · similarity 0.85)
- A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators (AAAI 2024 · 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.