Generating feature embeddings from a co-occurrence matrix

• Main Authors: EVANS COLIN HEARNE, SHAZEER NOAM M, DOHERTY RYAN P, WATERSON CHRISTOPHER ROBERT
• Format: Patent
• Language: Chinese; English
• Published: 31.08.2018
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

Methods, and systems, including computer programs encoded on computer storage media for generating compressed representations from a co-occurrence matrix. A method includes obtaining a set of sub matrices of a co-occurrence matrix, where each row of the co-occurrence matrix corresponds to a feature from a first feature vocabulary and each column of the co-occurrence matrix corresponds to a featurefrom a second feature vocabulary; selecting a sub matrix, wherein the sub matrix is associated with a particular row block and column block of the co-occurrence matrix; assigning respective d-dimensional initial row and column embedding vectors to each row and column from the particular row and column blocks, respectively; and determining a final row embedding vector and a final column embeddingvector by iteratively adjusting the initial row embedding vectors and the initial column embedding vectors using the co-occurrence matrix. 本发明描述了用于从同现矩阵生成压缩表示的方法和系统，包括编码在计算机存储介质上的计算机程序。方法包括：获得同现矩阵的组子矩阵，其中，所述同现矩阵的每行与来自第特征词表的特征相