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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper introduces a new data augmentation method for neural machinetranslation that can enforce stronger semantic consistency both within andacross languages. Our method is based on Conditional Masked Language Model(CMLM) which is bi-directional and can be conditional on both left and rightcontext, as well as the label. We demonstrate that CMLM is a good technique forgenerating context-dependent word distributions. In particular, we show thatCMLM is capable of enforcing semantic consistency by conditioning on bothsource and target during substitution. In addition, to enhance diversity, weincorporate the idea of soft word substitution for data augmentation whichreplaces a word with a probabilistic distribution over the vocabulary.Experiments on four translation datasets of different scales show that theoverall solution results in more realistic data augmentation and bettertranslation quality. Our approach consistently achieves the best performance incomparison with strong and recent works and yields improvements of up to 1.90BLEU points over the baseline.

Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model