US 11,755,570 B2
Memory-based neural network for question answering
Quan Tran, San Jose, CA (US); Walter Chang, San Jose, CA (US); and Franck Dernoncourt, San Jose, CA (US)
Assigned to ADOBE, INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Dec. 9, 2020, as Appl. No. 17/116,640.
Prior Publication US 2022/0179848 A1, Jun. 9, 2022
Int. Cl. G06F 7/00 (2006.01); G06F 16/242 (2019.01); G06F 40/40 (2020.01); H04L 51/02 (2022.01); G06N 3/08 (2023.01)
CPC G06F 16/243 (2019.01) [G06F 40/40 (2020.01); G06N 3/08 (2013.01); H04L 51/02 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
embedding an input phrase comprising a natural language query and a candidate answer from a set of candidate answers into an embedding space to obtain an embedded input phrase;
identifying a plurality of meta-evidence nodes in the embedding space based on the embedded input phrase, wherein each of the plurality of meta-evidence nodes represents a cluster of points in the embedding space, and wherein each point in the cluster of points is an embedding of a training example that includes a training query and a ground truth answer;
generating a support vector for the input phrase, wherein the support vector comprises a weighted sum of the plurality of meta-evidence nodes in the embedding space; and
selecting an answer to the natural language query from the set of candidate answers based on the support vector.