Generation of natural language processing model for information domain

A technology of natural language processing and natural language, which is applied in natural language data processing, natural language translation, electronic digital data processing, etc., and can solve the problems of low entry prohibition and time-consuming

Inactive Publication Date: 2014-08-20
IBM CORP
View PDF8 Cites 49 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The two known methods are rather time-consuming, the former has the advantage of being unambiguous and manually adjustable, while the latter is a black box, but does not offer low entry prohibitions, since only knowledge of the domain itself is required for the labeling task, where as in the former That way, some knowledge of the underlying matching technique is also required

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Generation of natural language processing model for information domain
  • Generation of natural language processing model for information domain
  • Generation of natural language processing model for information domain

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0118] Insurance providers want emails to be automatically correlated with relevant artifacts maintained in data repositories (ie, customers, policies, claims, etc.).

[0119] NLP models can be used to transform free-text resources (such as emails) as data by processing the contained text, marking references to relevant bits of information, such as names, policy numbers, claim IDs, and then mapping those to existing records.

example 2

[0121] Modelers need to verify that the bank model supports ISO20022 / Sepa requirements. SPEA is a new pan-European payment system introduced across the EU between 2007 and 2010. There are specific requirements for financial institutions or payment processors to become SPEA registered and SPEA compliant.

[0122] NLP models can process regulatory documents, identify necessary model requirements (concepts, relations, ...) and verify whether a given bank model provides the necessary support for those requirements.

example 3

[0124] An IBM consultant wants to more easily estimate the cost of upgrading Company X's existing infrastructure to a given healthcare model.

[0125] Company X hires IBM to revamp their data infrastructure based on the healthcare model provided by "Industry Models". A consultant is tasked with analyzing the capacity of Company X's systems and estimating the work involved in the upgrade. NLP models can be of great help in analyzing structural reports, architectural documents, etc. from Company X to identify missing concepts from existing architectures.

[0126] The natural language processing model generation system may be provided as a service to customers through a network.

[0127] The invention can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment containing both hardware and software elements. In a preferred embodiment, the invention is implemented in software including, but not limited to, firmware, resident software, mi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

Method and system are provided for generating a natural language processing model for an information domain. The method includes: deriving a skeleton of a natural language lexicon from a source model of the information domain; applying a set of syntactical rules defining concepts and relationships; and expanding the skeleton of the natural language lexicon based on reference documents from the information domain to provide a natural language processing model for the information domain, wherein expanding the skeleton includes clustering and scoring terms for concepts and relationships.

Description

technical field [0001] The present invention relates to the field of generative natural language processing models. In particular, the invention relates to generating natural language processing models for the information domain. Background technique [0002] Modern business analytics and processes rely heavily on information flowing through and around the business. Core business process information includes both transactional and textual data from sources such as emails, report documents, presentations, and instant messages. This information can be viewed as information flowing "through" traffic and originating from or within an authenticated community. [0003] The relative importance of the textual components of this information has increased over the years and is now recognized as a very important component. The textual composition of information is now largely unprocessed due to the difficulty of creating natural language processing (NLP) models for understanding thi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/27G06F40/00
CPCG06F17/241G06F17/218G06F17/2735G06F17/28G06F40/117G06F40/169G06F40/242G06F40/40
Inventor D·J·麦克洛斯基D·博尔佩里D·卡恩斯
Owner IBM CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap