Data Diversification: A Simple Strategy For Neural Machine Translation

By Xuan-Phi Nguyen, Shafiq R. Joty, Wu Kui, A. Aw. 2019

75 citations recorded by the source corpus.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Tao Qin
2. Tie-Yan Liu
3. Lijun Wu
4. Varun Prashant Gangal
5. Eduard H. Hovy
6. Teruko Mitamura
7. Soroush Vosoughi
8. Jason Wei

Citations in the corpus

• A Survey of Data Augmentation Approaches for NLP (2021, methodology): “Nguyen et al. (2020) propose D ATA D IVERSIFICATION which merges original training data with the predictions of several forward and backward models.”
• R-Drop: Regularized Dropout for Neural Networks (2021, methodology): “95) translation tasks, which surpass current SOTA models, such as the BERT-fused NMT [80] model that leverages large-scale monolingual data, and the Data Diversification [46] method trained with many translation models.”