Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020141421 - NATURAL LANGUAGE PROCESSING SHALLOW DISCOURSE PARSER

Publication Number WO/2020/141421
Publication Date 09.07.2020
International Application No. PCT/IB2019/061407
International Filing Date 27.12.2019
IPC
G06F 40/30 2020.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
30Semantic analysis
G06F 40/35 2020.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
30Semantic analysis
35Discourse or dialogue representation
G06F 40/211 2020.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
20Natural language analysis
205Parsing
211Syntactic parsing, e.g. based on context-free grammar or unification grammars
G06F 40/284 2020.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
20Natural language analysis
279Recognition of textual entities
284Lexical analysis, e.g. tokenisation or collocates
G06F 40/289 2020.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
20Natural language analysis
279Recognition of textual entities
289Phrasal analysis, e.g. finite state techniques or chunking
CPC
G06F 16/90332
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
90Details of database functions independent of the retrieved data types
903Querying
9032Query formulation
90332Natural language query formulation or dialogue systems
G06F 40/205
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
20Natural language analysis
205Parsing
G06F 40/284
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
20Natural language analysis
279Recognition of textual entities
284Lexical analysis, e.g. tokenisation or collocates
G06F 40/289
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
20Natural language analysis
279Recognition of textual entities
289Phrasal analysis, e.g. finite state techniques or chunking
G06F 40/30
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
30Semantic analysis
Applicants
  • 3M INNOVATIVE PROPERTIES COMPANY [US]/[US]
Inventors
  • KORNBLUTH, Jeremy R.
Agents
  • HUANG, X. Christina
  • FLORCZAK, Yen Tong,
  • BLANK, Colene H.,
  • HARTS, Dean M. ,
  • LEVINSON, Eric D.,
  • MAKI, Eloise J.,
  • NOWAK, Sandra K.,
  • RINGSRED, Ted K.,
Priority Data
62/786,63331.12.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) NATURAL LANGUAGE PROCESSING SHALLOW DISCOURSE PARSER
(FR) ANALYSEUR DE DISCOURS SUPERFICIEL À TRAITEMENT DE LANGAGE NATUREL
Abstract
(EN)
The present disclosure provides an improved methodology for constructing and querying a shallow discourse stack. Multiple shallow discourse stacks may be generated and queried, such as using a separate discourse stack for each semantic type. In an example, various discourse stacks may be used for semantic types associated with clinical concept identification and medical code extraction from medical records. The use of a shallow discourse stack may include identifying a concept of a specific semantic type as needed to resolve an under-specified complex concept, and the shallow discourse stack may be queried using the specific semantic type to resolve the under-specified complex concept. The formation and querying of the shallow discourse stack may be repeated throughout the document until all complex concepts are resolved.
(FR)
La présente invention concerne une méthodologie améliorée de construction et d'interrogation d'une pile de discours superficielle. De multiples piles de discours superficielles peuvent être générées et interrogées, par exemple à l'aide d'une pile de discours séparée pour chaque type sémantique. Dans un exemple, diverses piles de discours peuvent être utilisées pour des types sémantiques associés à une identification de concept clinique et à une extraction de code médical à partir d'enregistrements médicaux. L'utilisation d'une pile de discours superficielle peut comprendre l'identification d'un concept d'un type sémantique spécifique selon les besoins pour résoudre un concept complexe sous-spécifié, et la pile superficielle peut être interrogée à l'aide du type sémantique spécifique pour résoudre le concept complexe sous-spécifié. La formation et l'interrogation de la pile superficielle peuvent être répétées dans tout le document jusqu'à ce que tous les concepts complexes soient résolus.
Latest bibliographic data on file with the International Bureau