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 article firstly attempts to explore parallel algorithms of learningdistributed representations for both entities and relations in large-scaleknowledge repositories with {\it MapReduce} programming model on a multi-coreprocessor. We accelerate the training progress of a canonical knowledgeembedding method, i.e. {\it translating embedding} ({\bf TransE}) model, bydividing a whole knowledge repository into several balanced subsets, andfeeding each subset into an individual core where local embeddings canconcurrently run updating during the {\it Map} phase. However, it usuallysuffers from inconsistent low-dimensional vector representations of the samekey, which are collected from different {\it Map} workers, and further leads toconflicts when conducting {\it Reduce} to merge the various vectors associatedwith the same key. Therefore, we try several strategies to acquire the mergedembeddings which may not only retain the performance of {\it entity inference},{\it relation prediction}, and even {\it triplet classification} evaluated bythe single-thread {\bf TransE} on several well-known knowledge bases such asFreebase and NELL, but also scale up the learning speed along with the numberof cores within a processor. So far, the empirical studies show that we couldachieve comparable results as the single-thread {\bf TransE} performs by the{\it stochastic gradient descend} (SGD) algorithm, as well as increase thetraining speed multiple times via adapting the {\it batch gradient descend}(BGD) algorithm for {\it MapReduce} paradigm.

Parallel Knowledge Embedding with MapReduce on a Multi-core Processor