Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution
In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for the improvement of about +1 BLEU across four language pairs. Instead, we demonstrate that the improvement comes from three other factors unrelated to discourse: context diversity, length diversity, and (to a lesser extent) position shifting.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationDiversityLow Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationPositionTranslationSimilar Papers 제목 키워드 기반
From Scarcity to Efficiency: Investigating the Effects of Data Augmentation on African Machine Translation
The linguistic diversity across the African continent presents different challenges and opportunities for machine translation. This study explores the effects of data augmentation techniques in improving translation syst…
Machine TranslationData AugmentationSentence Concatenation Approach to Data Augmentation for Neural Machine Translation
Neural machine translation (NMT) has recently gained widespread attention because of its high translation accuracy. However, it shows poor performance in the translation of long sentences, which is a major issue in low-r…
Data AugmentationMachine TranslationNMTSentence+1Generalized Data Augmentation for Low-Resource Translation
Translation to or from low-resource languages LRLs poses challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing large amounts of monolingual data is regarded as an effective…
Data AugmentationMachine TranslationTranslationUnsupervised Machine TranslationTextual Augmentation Techniques Applied to Low Resource Machine Translation: Case of Swahili
In this work we investigate the impact of applying textual data augmentation tasks to low resource machine translation. There has been recent interest in investigating approaches for training systems for languages with l…
Data AugmentationMachine TranslationNMTtext-classification+2Roto-Translation Covariant Convolutional Networks for Medical Image Analysis
We propose a framework for rotation and translation covariant deep learning using $SE(2)$ group convolutions. The group product of the special Euclidean motion group $SE(2)$ describes how a concatenation of two roto-tran…
Data AugmentationMedical Image AnalysisTranslation