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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Transformer-based models have achieved great success on sentence pairmodeling tasks, such as answer selection and natural language inference (NLI).These models generally perform cross-attention over input pairs, leading toprohibitive computational costs. Recent studies propose dual-encoder and lateinteraction architectures for faster computation. However, the balance betweenthe expressive of cross-attention and computation speedup still needs bettercoordinated. To this end, this paper introduces a novel paradigm MixEncoder forefficient sentence pair modeling. MixEncoder involves a light-weightcross-attention mechanism. It conducts query encoding only once while modelingthe query-candidate interaction in parallel. Extensive experiments conducted onfour tasks demonstrate that our MixEncoder can speed up sentence pairing byover 113x while achieving comparable performance as the more expensivecross-attention models.

Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling