Probabilistic natural language processing using a likelihood vector
AssigneeIHC Intellectual Asset Management, LLC
InventorPeter J. Haug
Life of this patent
Estimating the term…
Abstract
A method for natural language processing on a computing device is described. The computing device receives a free text document. The computing device parses the free text document for gross structure. The gross structure includes sections, paragraphs and sentences. The computing device determines an application of at least one knowledge base. The free text document is parsed for fine structure on the computing device. The fine structure includes sub-sentences. The computing device applies the parsed document and at least one likelihood vector to a Bayesian network. The computing device outputs meanings and probabilities.
Claims20
A method for natural language processing on a computing device, comprising:
- receiving a free text document;
- parsing, on a computing device, the free text document for gross structure, wherein the gross structure comprises sections, paragraphs and sentences;
- determining, on the computing device, an application of at least one knowledge base;
- parsing the free text document for fine structure on the computing device, wherein the fine structure comprises sub-sentences;
- applying, on the computing device, the parsed document and at least one likelihood vector to a Bayesian network;
- and
- outputting meanings and probabilities from the computing device.
A computing device that is configured for natural language processing on a computing device, comprising:
- a processor;
- memory in electronic communication with the processor;
- instructions stored in the memory, the instructions being executable to:
- receive a free text document;
- parse the free text document for gross structure, wherein the gross structure comprises sections, paragraphs and sentences;
- determine an application of at least one knowledge base;
- parse the free text document for fine structure, wherein the fine structure comprises sub-sentences;
- apply the parsed document and at least one likelihood vector to a Bayesian network;
- and
- output meanings and probabilities.
Dependencies are inferred from the claim text.