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 present a novel supervised word alignment method based on cross-languagespan prediction. We first formalize a word alignment problem as a collection ofindependent predictions from a token in the source sentence to a span in thetarget sentence. As this is equivalent to a SQuAD v2.0 style question answeringtask, we then solve this problem by using multilingual BERT, which isfine-tuned on a manually created gold word alignment data. We greatly improvedthe word alignment accuracy by adding the context of the token to the question.In the experiments using five word alignment datasets among Chinese, Japanese,German, Romanian, French, and English, we show that the proposed methodsignificantly outperformed previous supervised and unsupervised word alignmentmethods without using any bitexts for pretraining. For example, we achieved anF1 score of 86.7 for the Chinese-English data, which is 13.3 points higher thanthe previous state-of-the-art supervised methods.

A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT