Pith. sign in

REVIEW

Dynamic Curriculum Learning for Low-Resource Neural Machine Translation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2011.14608 v1 pith:A2DU27BP submitted 2020-11-30 cs.CL

Dynamic Curriculum Learning for Low-Resource Neural Machine Translation

classification cs.CL
keywords trainingdatalow-resourcemachinesamplestranslationcompetencecurriculum
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. In this case, the way of using data appears to be more important. Here, we investigate the effective use of training data for low-resource NMT. In particular, we propose a dynamic curriculum learning (DCL) method to reorder training samples in training. Unlike previous work, we do not use a static scoring function for reordering. Instead, the order of training samples is dynamically determined in two ways - loss decline and model competence. This eases training by highlighting easy samples that the current model has enough competence to learn. We test our DCL method in a Transformer-based system. Experimental results show that DCL outperforms several strong baselines on three low-resource machine translation benchmarks and different sized data of WMT' 16 En-De.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.