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

BERT-enhanced neural machine translation (NMT) aims at leveragingBERT-encoded representations for translation tasks. A recently proposedapproach uses attention mechanisms to fuse Transformer's encoder and decoderlayers with BERT's last-layer representation and shows enhanced performance.However, their method doesn't allow for the flexible distribution of attentionbetween the BERT representation and the encoder/decoder representation. In thiswork, we propose a novel BERT-enhanced NMT model called BERT-JAM which improvesupon existing models from two aspects: 1) BERT-JAM uses joint-attention modulesto allow the encoder/decoder layers to dynamically allocate attention betweendifferent representations, and 2) BERT-JAM allows the encoder/decoder layers tomake use of BERT's intermediate representations by composing them using a gatedlinear unit (GLU). We train BERT-JAM with a novel three-phase optimizationstrategy that progressively unfreezes different components of BERT-JAM. Ourexperiments show that BERT-JAM achieves SOTA BLEU scores on multipletranslation tasks.

BERT-JAM: Boosting BERT-Enhanced Neural Machine Translation with Joint Attention