METHOD, DEVICE, AND APPARATUS FOR WORD VECTOR PROCESSING BASED ON CLUSTERS

摘要

A cluster-based word vector processing method, apparatus, and device are disclosed. The cluster includes a server cluster and a worker computer cluster. Each worker computer included in the worker computer cluster separately obtains a word and context words of the word that are extracted from a corpus (S202). The worker computer obtains word vectors for the word and the context words of the word (S204). The worker computer calculates a gradient according to the word, the context words of the word, and the word vectors (S206). The worker computer asynchronously updates the gradient to a server included in the server cluster (S208). The server updates the word vectors for the word and the context words of the word according to the gradient (S210).