公开(公告)号：US12019661B2

公开(公告)日：2024-06-25

申请号：US18126698

申请日：2023-03-27

Applicant: Merative US L.P.

Inventor： Robert C. Sizemore ,  Jennifer L. La Rocca ,  Sterling R. Smith ,  Mario J. Lorenzo ,  Kristin E. McNeil ,  David B. Werts

IPC: G06F16/332 ,  G06F16/31 ,  G06F16/33 ,  G06F16/335 ,  G06F40/169 ,  G16H15/00

CPC classification number: G06F16/3329 ,  G06F16/328 ,  G06F16/3344 ,  G06F16/335 ,  G06F40/169 ,  G16H15/00

Abstract: A mechanism is provided in a data processing system to implement an annotator for annotating content using context-based surface forms. The mechanism receives a dictionary data structure of surface forms comprising a plurality of regular expressions and input content. The mechanism compares a given span of text in the input content to each regular expression in the dictionary data structure. Responsive to the given span of text matching a given regular expression, an annotator annotates the span of text with a content indicator corresponding to a content category associated with the dictionary data structure. The mechanism performs a natural language processing operation on the input content based on results of the annotation.

公开(公告)号：US11748562B2

公开(公告)日：2023-09-05

申请号：US17851584

申请日：2022-06-28

Applicant: Merative US L.P.

Inventor： Robert C. Sizemore ,  David B. Werts ,  Sterling R. Smith

IPC: G06F40/205 ,  G06F40/14 ,  G06F40/279

CPC classification number: G06F40/205 ,  G06F40/14 ,  G06F40/279

Abstract: Mechanisms are provided to perform selective deep parsing of natural language content. A targeted deep parse natural language processing system is configured to recognize one or more triggers that specify elements within natural language content that indicate a portion of natural language content that is to be targeted with a deep parse operation. A portion of natural language content is received and a pre-deep parse scan operation is performed on the natural language content based on the one or more triggers to identify one or more sub-portions of the natural language content that contain at least one of the one or more triggers. A deep parse is performed on only the one or more sub-portions of the portion of natural language content that contain at least one of the one or more triggers, while other sub-portions of the portion of natural language content are not deep parsed.

公开(公告)号：US11625422B2

公开(公告)日：2023-04-11

申请号：US16700218

申请日：2019-12-02

Applicant: Merative US L.P.

Inventor： Robert C. Sizemore ,  Jennifer L. La Rocca ,  Sterling R. Smith ,  Mario J. Lorenzo ,  Kristin E. McNeil ,  David B. Werts

IPC: G06F16/332 ,  G06F16/31 ,  G06F40/169 ,  G06F16/335 ,  G16H15/00 ,  G06F16/33

Abstract: A mechanism is provided in a data processing system to implement an annotator for annotating content using context-based surface forms. The mechanism receives a dictionary data structure of surface forms comprising a plurality of regular expressions and input content. The mechanism compares a given span of text in the input content to each regular expression in the dictionary data structure. Responsive to the given span of text matching a given regular expression, an annotator annotates the span of text with a content indicator corresponding to a content category associated with the dictionary data structure. The mechanism performs a natural language processing operation on the input content based on results of the annotation.

公开(公告)号：US20230315765A1

公开(公告)日：2023-10-05

申请号：US18126698

申请日：2023-03-27

Applicant: Merative US L.P.

Inventor： Robert C. Sizemore ,  Jennifer L. La Rocca ,  Sterling R. Smith ,  Mario J. Lorenzo ,  Kristin E. Mcneil ,  David B. Werts

IPC: G06F16/332 ,  G16H15/00 ,  G06F16/31 ,  G06F40/169 ,  G06F16/335 ,  G06F16/33

CPC classification number: G06F16/3329 ,  G06F16/328 ,  G06F16/3344 ,  G06F16/335 ,  G06F40/169 ,  G16H15/00

Abstract: A mechanism is provided in a data processing system to implement an annotator for annotating content using context-based surface forms. The mechanism receives a dictionary data structure of surface forms comprising a plurality of regular expressions and input content. The mechanism compares a given span of text in the input content to each regular expression in the dictionary data structure. Responsive to the given span of text matching a given regular expression, an annotator annotates the span of text with a content indicator corresponding to a content category-associated with the dictionary data structure. The mechanism performs a natural language processing operation on the input content based on results of the annotation.