Research map / Label-efficient and robust learning / Domain adaptation and generalization
Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation
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 meta-curriculum learning instead of Meta-MT | Transformer NMT · COVID-19 | BLEU: 29.71 -> 30.46 | Helped |
| Use meta-curriculum learning instead of Meta-MT | Transformer NMT · Bible | BLEU: 17.66 -> 18.06 | Helped |
| Use meta-curriculum learning instead of Meta-MT | Transformer NMT · Books | BLEU: 14.99 -> 15.02 | Helped |
| Use meta-curriculum learning instead of Meta-MT | Transformer NMT · ECB | BLEU: 32.62 -> 33.44 | Helped |
| Use meta-curriculum learning instead of Meta-MT | Transformer NMT · TED | BLEU: 30.36 -> 30.37 | Helped |
| Use meta-curriculum learning instead of Meta-MT | Transformer NMT · EMEA | BLEU: 45.05 -> 45.91 | Helped |
| Use meta-curriculum learning instead of Meta-MT | Transformer NMT · GlobalVoices | BLEU: 27.84 -> 28.28 | Helped |
| Use meta-curriculum learning instead of Meta-MT | Transformer NMT · JRC | BLEU: 44.01 -> 44.85 | Helped |
| Use meta-curriculum learning instead of Meta-MT | Transformer NMT · KDE | BLEU: 31.24 -> 31.95 | Helped |
| Use meta-curriculum learning instead of Meta-MT | Transformer NMT · News | BLEU: 31.17 -> 32.00 | Helped |
| Fine-tune Meta-Curriculum on the target domain | Meta-Curriculum · COVID-19 | BLEU: 27.54 -> 30.46; +2.92 | Helped |
| Fine-tune Meta-Curriculum on the target domain | Meta-Curriculum · Bible | BLEU: 13.52 -> 18.06; +4.54 | Helped |
Closest papers by meaning
- MetaMT, a Meta Learning Method Leveraging Multiple Domain Data for Low Resource Machine Translation (AAAI 2020 · similarity 0.93)
- Reinforced Curriculum Learning on Pre-Trained Neural Machine Translation Models (AAAI 2020 · similarity 0.89)
- Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learning (AAAI 2023 · similarity 0.89)
- Meta Back-Translation (ICLR 2021 · similarity 0.88)
- Provable Meta-Learning with Low-Rank Adaptations (NeurIPS 2025 · similarity 0.86)
- A Benchmark for Learning to Translate a New Language from One Grammar Book (ICLR 2024 · 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.