Research map / Label-efficient and robust learning / Domain adaptation and generalization
Go From the General to the Particular: Multi-Domain Translation with Domain Transformation 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 |
|---|---|---|---|
| Add domain transformation networks | Transformer · Zh⇒En small balanced | BLEU (Avg.): 30.90 -> 32.34 | Helped |
| Add domain supervision to domain transformation | Domain Transformation · Zh⇒En small balanced | BLEU (Avg.): 32.34 -> 34.25 | Helped |
| Add domain transformation networks | Transformer · Zh⇒En large balanced | BLEU (Avg.): 41.45 -> 42.43 | Helped |
| Add domain supervision to domain transformation | Domain Transformation · Zh⇒En large balanced | BLEU (Avg.): 42.43 -> 42.93 | Helped |
| Add domain transformation networks | Transformer · De⇒En unbalanced | BLEU (Avg.): 48.68 -> 49.15 | Helped |
| Add domain supervision to domain transformation | Domain Transformation · De⇒En unbalanced | BLEU (Avg.): 49.15 -> 49.70 | Helped |
| Add domain transformation networks | Transformer · En⇒Fr unbalanced | BLEU (Avg.): 50.75 -> 51.52 | Helped |
| Add domain supervision to domain transformation | Domain Transformation · En⇒Fr unbalanced | BLEU (Avg.): 51.52 -> 51.83 | Helped |
| Add sequence-level distillation without domain transformation (ablation) | Transformer · Zh⇒En small balanced | BLEU: 30.90 -> 31.45 | Helped |
| Add word-level distillation without domain transformation (ablation) | Transformer · Zh⇒En small balanced | BLEU: 30.90 -> 31.51 | Helped |
| Add sequence-level distillation to domain transformation (ablation) | Domain Transformation · Zh⇒En small balanced | BLEU: 32.34 -> 32.70 | Helped |
| Add word-level distillation to domain transformation (ablation) | Domain Transformation · Zh⇒En small balanced | BLEU: 32.34 -> 33.05 | Helped |
Closest papers by meaning
- Learning to Transfer: Unsupervised Domain Translation via Meta-Learning (AAAI 2020 · similarity 0.88)
- MetaMT, a Meta Learning Method Leveraging Multiple Domain Data for Low Resource Machine Translation (AAAI 2020 · similarity 0.88)
- Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation (AAAI 2026 · similarity 0.88)
- Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge (NeurIPS 2024 · similarity 0.85)
- Adapting to Distribution Shift by Visual Domain Prompt Generation (ICLR 2024 · similarity 0.84)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 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.