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

Many document-level neural machine translation (NMT) systems have exploredthe utility of context-aware architecture, usually requiring an increasingnumber of parameters and computational complexity. However, few attention ispaid to the baseline model. In this paper, we research extensively the pros andcons of the standard transformer in document-level translation, and find thatthe auto-regressive property can simultaneously bring both the advantage of theconsistency and the disadvantage of error accumulation. Therefore, we propose asurprisingly simple long-short term masking self-attention on top of thestandard transformer to both effectively capture the long-range dependence andreduce the propagation of errors. We examine our approach on the two publiclyavailable document-level datasets. We can achieve a strong result in BLEU andcapture discourse phenomena.

Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation