Abstract
Manipulating training data leads to robust neural models for MT.
MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation
Related papers
Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).
- Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning (2020)74% match
- Multi-Domain Neural Machine Translation (2018)73% match
- Building a Multi-domain Neural Machine Translation Model using Knowledge Distillation (2020)71% match
- Training Mixed-Domain Translation Models via Federated Learning (2022)70% match
- Machine Translation Customization via Automatic Training Data Selection from the Web (2021)70% match
- Learning a Multi-Domain Curriculum for Neural Machine Translation (2019)69% match
- Finding the Right Recipe for Low Resource Domain Adaptation in Neural Machine Translation (2022)69% match
- Neural Machine Translation Training in a Multi-Domain Scenario (2017)69% match