MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation
arXiv:1912.05467 · doi:10.1609/aaai.v34i05.6339
Abstract
Manipulating training data leads to robust neural models for MT.
References in corpus (6)
- A Simple, Fast Diverse Decoding Algorithm for Neural Generation
- A Survey of Domain Adaptation for Neural Machine Translation
- Meta-Learning: A Survey
- An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation
- Large-scale Pretraining for Neural Machine Translation with Tens of Billions of Sentence Pairs
- Curriculum Learning for Domain Adaptation in Neural Machine Translation