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-Level Auto-Completion (WLAC) plays a crucial role in Computer-AssistedTranslation. It aims at providing word-level auto-completion suggestions forhuman translators. While previous studies have primarily focused on designingcomplex model architectures, this paper takes a different perspective byrethinking the fundamental question: what kind of words are goodauto-completions? We introduce a measurable criterion to answer this questionand discover that existing WLAC models often fail to meet this criterion.Building upon this observation, we propose an effective approach to enhanceWLAC performance by promoting adherence to the criterion. Notably, the proposedapproach is general and can be applied to various encoder-based architectures.Through extensive experiments, we demonstrate that our approach outperforms thetop-performing system submitted to the WLAC shared tasks in WMT2022, whileutilizing significantly smaller model sizes.

Rethinking Word-Level Auto-Completion in Computer-Aided Translation