Axiomatic Approach for Entity Attribution in Unstructured Data

• US 20140280008A1
• Filed: 03/15/2013
• Published: 09/18/2014
• Est. Priority Date: 03/15/2013
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Boudreau, Michael K., Moore, Bradley T., Mousaad, Ahmed, Trim, Craig M.
• Application Number:
  US13/833,899
• Publication Number:
  US 20140280008A1
• Time in Patent Office: Days
• US Class Current: 707/708
• CPC Class Codes: G06F 16/367 Ontology

Abstract

The present specification relates to Ontology modeling, and, more specifically, to systems and methods for populating a triple store (RDF Graph) data structure from a parse tree diagram and producing a measurable increased degree of confidence in the reliability of the inferences based on the matched axioms derived from the ontology model. The steps of populating and producing can be performed automatically.

Claims

1. A computer implemented method for associating a confidence level to axioms derived from an augmented ontology model, the method comprising:

parsing, by a processor, unstructured source data;

generating, by said processor, a first parse tree from the parsed unstructured source data;

constructing, by said processor, an ontology model based on the first parse tree;

augmenting, by said processor, the ontology model with data from an external ontology model augmentation source;

establishing, by said processor, instance data based on the augmented ontology model;

establishing, by said processor, a first axiom from the augmented ontology model;

expanding, by said processor, the first axiom into a plurality of axioms, each of which is a variation of the first axiom and is part of the instance data;

associating, by said processor, a confidence level to each of the first axiom and the plurality of axioms with variations.

2. The method of claim 1, further comprising the step of annotating, by the processor, partial axioms within the parsed unstructured source data.

3. The method of claim 1, wherein the step of associating, by said processor, a confidence level to each of the first axiom and the plurality of axioms with variations further comprises creating a database of axiom data comprising the first axiom and the plurality of axioms with variations and associated confidence levels.

4. The method of claim 3, further comprises matching one of the first axiom and the plurality of axioms with variations with unstructured text within the unstructured source data, and inferring attributes about the unstructured text with a particular confidence level.

5. The method of claim 1, wherein the external ontology model augmentation source is a lexical database.

6. The method of claim 5, wherein the step of augmenting, by said processor, the ontology model with data from the external ontology model augmentation source further comprises the step of augmenting, by said processor, the ontology model with hyponyms obtained from the lexical database.

7. The method of claim 5, wherein the step of augmenting, by said processor, the ontology model with data from the external ontology model augmentation source further comprises the step of augmenting, by said processor, the ontology model with troponymes obtained from the lexical database.

10. The method of claim 1, further comprising a database of axiom data connected to said axiom confidence level establishment module comprising the first axiom and the plurality of axioms with variations and associated confidence levels.

11. The method of claim 3, further comprising an NLP engine configured to match one of the first axiom and the plurality of axioms with variations with unstructured text within the unstructured source data, and to infer attributes about the unstructured text with a particular confidence level.

8. A system for associating a confidence level to axioms derived from an augmented ontology model comprising:

a parsing module programmed to parse unstructured source data;

a generation module connected to said parsing module and programmed to generate a first parse tree from the parsed unstructured source data;

a model ontology module connected to the generation module and programmed to construct an ontology model based on the first parse tree, wherein said model ontology module comprises an input configured to receive data from an external ontology model augmentation source and is programmed to augment the ontology model with the data from the external ontology model augmentation source;

a model axioms module connected to said model ontology module and programmed to establish instance data based on the augmented ontology model, to establish a first axiom from the augmented ontology model, and to expand the first axiom into a plurality of axioms, each of which is a variation of the first axiom and is part of the instance data; and

an axiom confidence level establishment module connected to said model axioms module and programmed to associate a confidence level to each of the first axiom and the plurality of axioms with variations.

9. The system of claim 8, further comprising an annotation module programmed to annotate partial axioms within the parsed unstructured source data.

12. The method of claim 8, wherein the external ontology model augmentation source is a lexical database.

13. The method of claim 12, wherein said model ontology module step is further programmed to augment the ontology model with hyponyms obtained from the lexical database.

14. The method of claim 12, wherein said model ontology module step is further programmed to augment the ontology model with troponymes obtained from the lexical database.