Curriculum Learning and Minibatch Bucketing in Neural Machine Translation

Tom Kocmi, Ondřej Bojar
2017 RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning  
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.
doi:10.26615/978-954-452-049-6_050 dblp:conf/ranlp/KocmiB17 fatcat:3432tnq73zezvpzkymhdwcmhqe