paper-with-me

Papers

Deterministic Reversible Data Augmentation for Neural Machine Translation

2024-06-04 · Jiashu Yao, Heyan Huang, Zeming Liu, Yuhang Guo

Data augmentation is an effective way to diversify corpora in machine translation, but previous methods may introduce semantic inconsistency between original and augmented data because of irreversible operations and random subword sampling procedures. To generate both symbolically diverse and semantically consistent augmentation data, we propose Deterministic Reversible Data Augmentation (DRDA), a simple but effective data augmentation method for neural machine translation. DRDA adopts deterministic segmentations and reversible operations to generate multi-granularity subword representations and pulls them closer together with multi-view techniques. With no extra corpora or model changes required, DRDA outperforms strong baselines on several translation tasks with a clear margin (up to 4.3 BLEU gain over Transformer) and exhibits good robustness in noisy, low-resource, and cross-domain datasets.

📄 PDF Abstract BibTeX arXiv:2406.02517

Code (1)

BITHLP/DRDA 공식 구현 pytorch

Tasks

Data AugmentationMachine TranslationTranslation

Similar Papers 제목 키워드 기반

Duplex Sequence-to-Sequence Learning for Reversible Machine Translation

2021-05-07 · NeurIPS 2021 12 · Zaixiang Zheng, Hao Zhou, ShuJian Huang, Jiajun Chen 외

Sequence-to-sequence learning naturally has two directions. How to effectively utilize supervision signals from both directions? Existing approaches either require two separate models, or a multitask-learned model but wi…

Machine TranslationTranslation

Multi-split Reversible Transformers Can Enhance Neural Machine Translation

2021-04-01 · EACL 2021 2 · Yuekai Zhao, Shuchang Zhou, Zhihua Zhang

Large-scale transformers have been shown the state-of-the-art on neural machine translation. However, training these increasingly wider and deeper models could be tremendously memory intensive. We reduce the memory burde…

Machine TranslationTranslation

Time-Reversible Bridges of Data with Machine Learning

2024-12-18 · Ludwig Winkler

The analysis of dynamical systems is a fundamental tool in the natural sciences and engineering. It is used to understand the evolution of systems as large as entire galaxies and as small as individual molecules. With pr…

Numerical Integration

OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language models

2023-11-24 · Nikolay Bogoychev, Jelmer Van der Linde, Graeme Nail, Barry Haddow 외

Developing high quality machine translation systems is a labour intensive, challenging and confusing process for newcomers to the field. We present a pair of tools OpusCleaner and OpusTrainer that aim to simplify the pro…

Data AugmentationMachine TranslationSchedulingTranslation

Bayesian Layers: A Module for Neural Network Uncertainty

2018-12-10 · NeurIPS 2019 12 · Dustin Tran, Michael W. Dusenberry, Mark van der Wilk, Danijar Hafner

We describe Bayesian Layers, a module designed for fast experimentation with neural network uncertainty. It extends neural network libraries with drop-in replacements for common layers. This enables composition via a uni…

Gaussian ProcessesMachine TranslationProbabilistic ProgrammingTranslation