SYSTEM AND METHOD FOR LANGUAGE EXTRACTION AND ENCODING

• US 20140142924A1
• Filed: 01/28/2014
• Published: 05/22/2014
• Est. Priority Date: 07/29/2011
• Status: Active Application

• Current Assignee: Trustees Of Columbia University In The City Of New York (Columbia University)
• Original Assignee: Trustees Of Columbia University In The City Of New York (Columbia University)
• Inventors: Friedman, Carol
• Granted Patent: US 10,275,424 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/279 Recognition of textual entities

Abstract

Improved systems and methods for extracting information from medical and natural-language text data.

Claims

1. A method for extracting information from medical or natural-language input text, comprising:

receiving medical or natural-language input text;

utilizing a lexicon knowledge base to identify and categorize multi-word and single word phrases within sentences of the input text;

parsing said input text to determine the grammatical structure of the text data, said parsing step comprising the step of referring to a domain parameter having a value indicative of a domain from which the text data originated, the domain parameter corresponding to one or more rules of grammar within a knowledge base related to the domain to be applied for parsing the text data;

regularizing the parsed text data to form structured word terms; and

tagging the text data with a structured data component derived from the structured word terms.

2. The method of claim 1, wherein said lexicon knowledge base is customized by a user.

3. The method of claim 1, wherein one or more words or portions of said medical or natural-language input text is tagged with an identification tag for recognition and sorting.

4. The method of claim 3, wherein said portions of said medical or natural-language input text that is tagged is selected from the group consisting of dates, names, phone numbers, addresses, and locations.

5. The method of claim 1, wherein output is generated for storing the output in a form compatible with a standard spreadsheet application or relational database.

6. The method of claim 1, further comprising generating a coding table.

7. A system for extracting information from medical or natural-language input text, comprising:

a lexicon knowledge base to identify and categorize multi-word and single word phrases within sentences of the input text;

a processor receiving said medical or natural-language input text coupled to said lexicon knowledge base;

a boundary identifier, coupled to said processor and said lexicon knowledge base and receiving said medical or natural-language input text; and

a parser, coupled to said boundary identifier and receiving said input text to determine the grammatical structure of the text data.

8. The system of claim 7, wherein said lexicon knowledge base is customized by a user.

9. The system of claim 7, wherein one or more words or portions of said medical or natural-language input text is tagged with an identification tag for recognition and sorting.

10. The system of claim 8, wherein said portions of said medical or natural-language input text that is tagged is selected from the group consisting of dates, names, phone numbers, addresses, and locations.

11. The system of claim 7, wherein output is generated for storing the output in a form compatible with a standard spreadsheet application or relational database.