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

We conduct a large-scale fine-grained comparative analysis of machinetranslations (MT) against human translations (HT) through the lens ofmorphosyntactic divergence. Across three language pairs and two types ofdivergence defined as the structural difference between the source and thetarget, MT is consistently more conservative than HT, with less morphosyntacticdiversity, more convergent patterns, and more one-to-one alignments. Throughanalysis on different decoding algorithms, we attribute this discrepancy to theuse of beam search that biases MT towards more convergent patterns. This biasis most amplified when the convergent pattern appears around 50% of the time intraining data. Lastly, we show that for a majority of morphosyntacticdivergences, their presence in HT is correlated with decreased MT performance,presenting a greater challenge for MT systems.

To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation