English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In Neural Machine Translation (NMT), data augmentation methods such asback-translation have proven their effectiveness in improving translationperformance. In this paper, we propose a novel data augmentation approach forNMT, which is independent of any additional training data. Our approach, AdMix,consists of two parts: 1) introduce faint discrete noise (word replacement,word dropping, word swapping) into the original sentence pairs to formaugmented samples; 2) generate new synthetic training data by softly mixing theaugmented samples with their original samples in training corpus. Experimentson three translation datasets of different scales show that AdMix achievessignifi cant improvements (1.0 to 2.7 BLEU points) over strong Transformerbaseline. When combined with other data augmentation techniques (e.g.,back-translation), our approach can obtain further improvements.

AdMix: A Mixed Sample Data Augmentation Method for Neural Machine Translation