Work

Curriculum Learning and Minibatch Bucketing in Neural Machine Translation

Year: 2017
Type: conference-paper
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.
Institution: Charles University
Language: English
Open Access status: bronze
OpenAlex ID: W2741838462
FWCI: 4.184
Cites: 24
Cited by: 185
Related to: 10