Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
2017pp. 379–386
Citations Over TimeTop 10% of 2017 papers
Abstract
We examine the effects of particular orderings of sentence pairs on the on-line training of neural machine translation (NMT). We focus on two types of such orderings: (1) ensuring that each minibatch contains sentences similar in some aspect and (2) gradual inclusion of some sentence types as the training progresses (so called "curriculum learning"). In our English-to-Czech experiments, the internal homogeneity of minibatches has no effect on the training but some of our "curricula" achieve a small improvement over the baseline.
Related Papers
- → The Czech Republic(2009)6 cited
- Kriminalita České republiky(2012)
- Sarah Kane's Plays in the Context of the Czech Republic(2012)
- → SOME EDUCATIONAL ASPECTS OF QUANTITATIVE LINGUISTIC ANALYSIS OF CZECH SIGN LANGUAGE(2019)
- → Havránek, Bohuslav (1893–1978)(2006)