Invention Grant
- Patent Title: Generating feature embeddings from a co-occurrence matrix
-
Application No.: US15424671Application Date: 2017-02-03
-
Publication No.: US10685012B2Publication Date: 2020-06-16
- Inventor: Noam M. Shazeer , Colin Hearne Evans , Christopher Robert Waterson , Ryan P. Doherty
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06F16/23
- IPC: G06F16/23 ; G06F16/31 ; G06F16/332 ; G06F16/33 ; G06K9/62 ; G06F40/44 ; G06F17/16 ; G06N5/04

Abstract:
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 feature from 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 embedding vector by iteratively adjusting the initial row embedding vectors and the initial column embedding vectors using the co-occurrence matrix.
Public/Granted literature
- US20170228414A1 GENERATING FEATURE EMBEDDINGS FROM A CO-OCCURRENCE MATRIX Public/Granted day:2017-08-10
Information query