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

Word alignment has proven to benefit many-to-many neural machine translation(NMT). However, high-quality ground-truth bilingual dictionaries were used forpre-editing in previous methods, which are unavailable for most language pairs.Meanwhile, the contrastive objective can implicitly utilize automaticallylearned word alignment, which has not been explored in many-to-many NMT. Thiswork proposes a word-level contrastive objective to leverage word alignmentsfor many-to-many NMT. Empirical results show that this leads to 0.8 BLEU gainsfor several language pairs. Analyses reveal that in many-to-many NMT, theencoder's sentence retrieval performance highly correlates with the translationquality, which explains when the proposed method impacts translation. Thismotivates future exploration for many-to-many NMT to improve the encoder'ssentence retrieval performance.

When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?