Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation

About

In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT). We formulate the design of a data augmentation policy with desirable properties as an optimization problem, and derive a generic analytic solution. This solution not only subsumes some existing augmentation schemes, but also leads to an extremely simple data augmentation strategy for NMT: randomly replacing words in both the source sentence and the target sentence with other random words from their corresponding vocabularies. We name this method SwitchOut. Experiments on three translation datasets of different scales show that SwitchOut yields consistent improvements of about 0.5 BLEU, achieving better or comparable performances to strong alternatives such as word dropout (Sennrich et al., 2016a). Code to implement this method is included in the appendix.

Xinyi Wang, Hieu Pham, Zihang Dai, Graham Neubig• 2018

Related benchmarks

TaskDatasetResultRank
Machine TranslationWMT En-De 2014 (test)
BLEU27.6
379
Machine TranslationIWSLT De-En 2014 (test)
BLEU35.9
146
Machine TranslationIWSLT En-De 2014 (test)
BLEU29
92
Machine TranslationIWSLT De-En 14
BLEU Score35.9
33
Instruction FollowingSCAN jump
Accuracy0.98
18
Machine TranslationIWSLT17 En-Fr (test)
BLEU39.49
18
Machine TranslationIWSLT Fr-En 2017 (test)
BLEU38.2
14
Language-driven NavigationSCAN Simple v1.0
Accuracy0.99
12
Language-driven NavigationSCAN around right v1.0
Accuracy0.97
8
Language-driven NavigationSCAN v1.0 (Length)
Accuracy17
6
Showing 10 of 10 rows

Other info

Follow for update