Natural language parsing method to provide conceptual flow

• US 8,725,493 B2
• Filed: 04/11/2008
• Issued: 05/13/2014
• Est. Priority Date: 01/06/2004
• Status: Active Grant

• Current Assignee: Neuric, LLC
• Original Assignee: Neuric, LLC
• Inventors: Womack, Lukas K., Visel, Thomas A., Fettig, Matthew, Lindsley, Hannah, Ledbetter, Micah
• Primary Examiner(s): SPOONER, LAMONT M
• Application Number:
  US12/101,904
• Publication Number:
  US 20080228467A1
• Time in Patent Office: 2,223 Days
• Field of Search: 704/1, 704/9, 704/10, 707706-708
• US Class Current: 704/9
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

A method for parsing the flow of natural human language to convert a flow of machine recognizable language into a conceptual flow includes, first, recognizing the lexical structure and then, a basic semantic grouping is determined for the language flow in the lexical structure. The basic semantic grouping is then determined that denotes the main action, occurrence or state of being for the language flow. The responsibility of the main action, occurrence or state of being for the language flow is then determined within the lexical structure followed by semantically parsing the lexical structure. Thereafter, any ambiguities in the responsibilities are resolved in a recursive manner by applying a predetermined set of rules thereto.

Claims

1. A method for parsing the flow of natural human language to convert the flow of natural human language represented by a flow of machine recognizable language into a conceptual flow defined by relationships among a plurality of stored concept neurons in a database, wherein each concept neuron represents a concept that is given meaning by the relationships of a given one of the concept neurons to other of the concept neurons, comprising the steps of:

receiving as an input the flow of machine recognizable language as a language flow that is comprised in part of a lexical structure;

recognizing the lexical structure by an artificial brain operating on a processing system;

determining a basic semantic grouping structure for the language flow in the lexical structure;

semantically parsing the lexical structure of the basic semantic grouping;

determining in the determined basic semantic grouping the main action, occurrence or state of being for the language flow in the parsed lexical structure and mapping it to a related one or more of the concept neurons;

determining the semantic role of the main action, occurrence or state of being for the language flow within the parsed lexical structure of the basic semantic grouping;

determining if ambiguities exists in the determined semantic role if the semantic role maps to more than one of the concept neurons;

resolving the ambiguities in the semantic role in a recursive manner by applying a predetermined set of rules thereto;

determining the semantic role of other portions of the parsed lexical structures relative to the semantic role of the main action, occurrence or state of being for the language flow and mapping them to concept neurons; and

forming a clump neuron that is associated with the basic semantic grouping and that embodies relationships between concept neurons identified in the lexical structure in order to represent the lexical structure in a conceptual form as a sequence of concept neurons and their related roles within the lexical structures.

2. The method of claim 1, wherein the basic semantic groupings are words.

3. The method of claim 1, wherein the lexical structure comprises a flow of sentences.

4. The method of claim 3, wherein the main action, occurrence or state of being for the language flow comprises the main verb.

5. The method of claim 4, wherein the step of determining the basic semantic grouping further comprises selecting the main verb from among a plurality of possible main verbs.

6. The method of claim 1, wherein the step of determining the semantic role further comprises determining a semantic role of the main action, occurrence or state of being for the language flow within the lexical structure.

7. The method of claim 1, wherein semantically parsing the lexical structure includes grammatically parsing the lexical structure.

8. The method of claim 1 further comprising repeating the step of determining the basic semantic grouping that denotes the main action, occurrence or state of being for the language flow upon resolving the ambiguities.

9. The method of claim 1, wherein the ambiguity comprises a lexical ambiguity in the lexical structure.

10. The method of claim 1, wherein the ambiguity comprises a structural ambiguity in the lexical structure.

11. The method of claim 1, wherein the predetermined set of rules comprise predetermined language rules.