paper-with-me

홈 › Papers

Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution

2021-05-04 · ACL (IWSLT) 2021 8 · Toan Q. Nguyen, Kenton Murray, David Chiang

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.

📄 PDF Abstract BibTeX arXiv:2105.01691

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDiversityLow Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationPositionTranslation

Similar Papers 제목 키워드 기반

From Scarcity to Efficiency: Investigating the Effects of Data Augmentation on African Machine Translation

2025-09-09 · Mardiyyah Oduwole, Oluwatosin Olajide, Jamiu Suleiman, Faith Hunja 외 arxiv

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 Augmentation

Sentence Concatenation Approach to Data Augmentation for Neural Machine Translation

2021-04-17 · NAACL 2021 4 · Seiichiro Kondo, Kengo Hotate, Masahiro Kaneko, Mamoru Komachi

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+1

Generalized Data Augmentation for Low-Resource Translation

2019-06-10 · ACL 2019 7 · Mengzhou Xia, Xiang Kong, Antonios Anastasopoulos, Graham Neubig

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 Translation

Textual Augmentation Techniques Applied to Low Resource Machine Translation: Case of Swahili

2023-06-12 · Catherine Gitau, Vukosi Marivate

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+2

Roto-Translation Covariant Convolutional Networks for Medical Image Analysis

2018-04-10 · Erik J. Bekkers, Maxime W. Lafarge, Mitko Veta, Koen AJ Eppenhof 외

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