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

This paper describes the Microsoft Translator submissions to the WMT19 newstranslation shared task for English-German. Our main focus is document-levelneural machine translation with deep transformer models. We start with strongsentence-level baselines, trained on large-scale data created viadata-filtering and noisy back-translation and find that back-translation seemsto mainly help with translationese input. We explore fine-tuning techniques,deeper models and different ensembling strategies to counter these effects.Using document boundaries present in the authentic and synthetic parallel data,we create sequences of up to 1000 subword segments and train transformertranslation models. We experiment with data augmentation techniques for thesmaller authentic data with document-boundaries and for larger authentic datawithout boundaries. We further explore multi-task training for theincorporation of document-level source language monolingual data via theBERT-objective on the encoder and two-pass decoding for combinations ofsentence-level and document-level systems. Based on preliminary humanevaluation results, evaluators strongly prefer the document-level systems overour comparable sentence-level system. The document-level systems also seem toscore higher than the human references in source-based direct assessment.

Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation