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

Accurate terminology translation is crucial for ensuring the practicality andreliability of neural machine translation (NMT) systems. To address this,lexically constrained NMT explores various methods to ensure pre-specifiedwords and phrases appear in the translation output. However, in many cases,those methods are studied on general domain corpora, where the terms are mostlyuni- and bi-grams (>98%). In this paper, we instead tackle a more challengingsetup consisting of domain-specific corpora with much longer n-gram and highlyspecialized terms. Inspired by the recent success of masked span predictionmodels, we propose a simple and effective training strategy that achievesconsistent improvements on both terminology and sentence-level translation forthree domain-specific corpora in two language pairs.

Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction