公开(公告)号：US11768869B2

公开(公告)日：2023-09-26

申请号：US17170520

申请日：2021-02-08

Applicant: ADOBE INC.

Inventor： Nedim Lipka ,  Seyedsaed Rezayidemne ,  Vishwa Vinay ,  Ryan Rossi ,  Franck Dernoncourt ,  Tracy Holloway King

IPC: G06F16/50 ,  G06N5/02 ,  G06F40/20 ,  G06F16/532 ,  G06F16/55 ,  G06F16/56

CPC classification number: G06F16/532 ,  G06F16/55 ,  G06F16/56 ,  G06F40/20 ,  G06N5/02

Abstract: The present disclosure describes systems and methods for information retrieval. Embodiments of the disclosure provide a retrieval network that leverages external knowledge to provide reformulated search query suggestions, enabling more efficient network searching and information retrieval. For example, a search query from a user (e.g., a query mention of a knowledge graph entity that is included in a search query from a user) may be added to a knowledge graph as a surrogate entity via entity linking. Embedding techniques are then invoked on the updated knowledge graph (e.g., the knowledge graph that includes additional edges between surrogate entities and other entities of the original knowledge graph), and entities neighboring the surrogate entity are retrieved based on the embedding (e.g., based on a computed distance between the surrogate entity and candidate entities in the embedding space). Search results can then be ranked and displayed based on relevance to the neighboring entity.

公开(公告)号：US20220253477A1

公开(公告)日：2022-08-11

申请号：US17170520

申请日：2021-02-08

Applicant: ADOBE INC.

Inventor： NEDIM LIPKA ,  Seyedsaed Rezayidemne ,  Vishwa Vinay ,  Ryan Rossi ,  Franck Dernoncourt ,  Tracy Holloway King

IPC: G06F16/532 ,  G06N5/02 ,  G06F16/56 ,  G06F16/55 ,  G06F40/20

Abstract: The present disclosure describes systems and methods for information retrieval. Embodiments of the disclosure provide a retrieval network that leverages external knowledge to provide reformulated search query suggestions, enabling more efficient network searching and information retrieval. For example, a search query from a user (e.g., a query mention of a knowledge graph entity that is included in a search query from a user) may be added to a knowledge graph as a surrogate entity via entity linking. Embedding techniques are then invoked on the updated knowledge graph (e.g., the knowledge graph that includes additional edges between surrogate entities and other entities of the original knowledge graph), and entities neighboring the surrogate entity are retrieved based on the embedding (e.g., based on a computed distance between the surrogate entity and candidate entities in the embedding space). Search results can then be ranked and displayed based on relevance to the neighboring entity.