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

This paper investigates an unsupervised approach towards deriving auniversal, cross-lingual word embedding space, where words with similarsemantics from different languages are close to one another. Previousadversarial approaches have shown promising results in inducing cross-lingualword embedding without parallel data. However, the training stage showsinstability for distant language pairs. Instead of mapping the source languagespace directly to the target language space, we propose to make use of asequence of intermediate spaces for smooth bridging. Each intermediate spacemay be conceived as a pseudo-language space and is introduced via simple linearinterpolation. This approach is modeled after domain flow in computer vision,but with a modified objective function. Experiments on intrinsic BilingualDictionary Induction tasks show that the proposed approach can improve therobustness of adversarial models with comparable and even better precision.Further experiments on the downstream task of Cross-Lingual Natural LanguageInference show that the proposed model achieves significant performanceimprovement for distant language pairs in downstream tasks compared tostate-of-the-art adversarial and non-adversarial models.

Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation