公开(公告)号：US20220100772A1

公开(公告)日：2022-03-31

申请号：US17039887

申请日：2020-09-30

Applicant: Amazon Technologies, Inc.

Inventor： Srikanth Doss Kadarundalagi Raghura ,  Yogarshi Paritosh Vyas ,  Miguel Ballesteros Martinez ,  Yahor Pushkin ,  Sunil Mallya Kasaragod ,  Yaser Al-Onaizan ,  Sameer Karnik ,  Abhinav Goyal ,  Graham Vintcent Horwood ,  Kapil Singh Badesara

IPC: G06F16/25 ,  G06F16/23 ,  G06F21/62 ,  G06F40/289

Abstract: Methods, systems, and computer-readable media for context-sensitive linking of entities to private databases are disclosed. An entity linking service stores a plurality of representations of entities. Individual ones of the entities correspond to individual ones of a plurality of records in one or more private databases. The entity linking service determines a mention of an entity in a document. The entity linking service selects, from the plurality of records in the one or more private databases, a record corresponding to the entity. The record is selected based at least in part on the plurality of representations of the entities and based at least in part on a context of the mention of the entity in the document. The entity linking service generates output comprising a reference to the selected record in the one or more private databases.

公开(公告)号：US11847406B1

公开(公告)日：2023-12-19

申请号：US17217807

申请日：2021-03-30

Applicant: Amazon Technologies, Inc.

Inventor： Sunil Mallya Kasaragod ,  Yahor Pushkin ,  Saman Zarandioon ,  Graham Vintcent Horwood ,  Miguel Ballesteros Martinez ,  Yogarshi Paritosh Vyas ,  Yinxiao Zhang ,  Diego Marcheggiani ,  Yaser Al-Onaizan ,  Xuan Zhu ,  Liutong Zhou ,  Yusheng Xie ,  Aruni Roy Chowdhury ,  Bo Pang

IPC: G06F17/00 ,  G06F40/143 ,  G06F40/169 ,  G06N20/00 ,  G06F40/154 ,  G06F40/103 ,  G06F40/284

CPC classification number: G06F40/143 ,  G06F40/103 ,  G06F40/154 ,  G06F40/169 ,  G06F40/284 ,  G06N20/00

Abstract: Techniques for performing natural language processing (NLP) on semi-structured data are described. An exemplary method includes receiving a semi-structured document to perform NLP on using a trained NLP model; converting the semi-structured document into a secondary format, wherein the secondary format includes spatial information for tokens of the semi-structured document; flattening the converted, secondary formatted semi-structured document into a Unicode Transformation Format text file; performing NLP on the Unicode Transformation Format text file using the trained NLP model; and providing a result of the NLP to a requester.