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

While numerous studies have been conducted in the literature exploringdifferent types of machine learning approaches for search ranking, most of themare focused on specific pre-defined problems but only a few of them havestudied the ranking framework which can be applied in a commercial searchengine in a scalable way. In the meantime, existing ranking models are oftenoptimized for normalized discounted cumulative gains (NDCG) or onlineclick-through rate (CTR), and both types of machine learning models are builtbased on the assumption that high-quality training data can be easily obtainedand well applied to unseen cases. In practice at Facebook search, we observedthat our training data for ML models have certain issues. First, tail queryintents are hardly covered in our human rating dataset. Second, search clicklogs are often noisy and hard to clean up due to various reasons. To addressthe above issues, in this paper, we propose a probabilistic intent basedranking framework (short for piRank), which can: 1) provide a scalableframework to address various ranking issues for different query intents in adivide-and-conquer way; 2) improve system development agility includingiteration speed and system debuggability; 3) combine both machine learning andempirical-based algorithmic methods in a systematic way. We conducted extensiveexperiments and studies on top of Facebook search engine system and validatedthe effectiveness of this new ranking architecture.

piRank: A Probabilistic Intent Based Ranking Framework for Facebook Search