US 12,190,621 B2
Generating weighted contextual themes to guide unsupervised keyphrase relevance models
Debraj Debashish Basu, Los Angeles, CA (US); Shankar Venkitachalam, San Jose, CA (US); Vinh Khuc, Campbell, CA (US); and Deepak Pai, Sunnyvale, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Mar. 3, 2022, as Appl. No. 17/653,414.
Prior Publication US 2023/0282018 A1, Sep. 7, 2023
Int. Cl. G06F 17/00 (2019.01); G06F 40/295 (2020.01); G06N 20/00 (2019.01); G06V 30/19 (2022.01); G06V 30/416 (2022.01)
CPC G06V 30/416 (2022.01) [G06F 40/295 (2020.01); G06N 20/00 (2019.01); G06V 30/19113 (2022.01); G06V 30/19127 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium comprising instructions that, when executed by at least one processing device, cause the at least one processing device to perform operations comprising:
generating a graph from a digital document by mapping words from the digital document to nodes of the graph;
determining named entity bias weights for the nodes of the graph utilizing frequencies with which the words corresponding to the nodes appear within named entities extracted from the digital document utilizing a named entity recognition model and numbers of instances that the words appear within the named entities; and
generating a keyphrase summary for the digital document utilizing the graph and a machine learning model biased according to the named entity bias weights for the nodes of the graph.