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

Interactive and non-interactive model are the two de-facto standardframeworks in vector-based cross-lingual information retrieval (V-CLIR), whichembed queries and documents in synchronous and asynchronous fashions,respectively. From the retrieval accuracy and computational efficiencyperspectives, each model has its own superiority and shortcoming. In thispaper, we propose a novel framework to leverage the advantages of these twoparadigms. Concretely, we introduce semi-interactive mechanism, which buildsour model upon non-interactive architecture but encodes each document togetherwith its associated multilingual queries. Accordingly, cross-lingual featurescan be better learned like an interactive model. Besides, we further transferknowledge from a well-trained interactive model to ours by reusing its wordembeddings and adopting knowledge distillation. Our model is initialized from amultilingual pre-trained language model M-BERT, and evaluated on twoopen-resource CLIR datasets derived from Wikipedia and an in-house datasetcollected from a real-world search engine. Extensive analyses reveal that ourmethods significantly boost the retrieval accuracy while maintaining thecomputational efficiency.

Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval