Determining base attributes for terms

• US 8,577,924 B2
• Filed: 12/15/2008
• Issued: 11/05/2013
• Est. Priority Date: 12/15/2008
• Status: Active Grant

• Current Assignee: Forcepoint Federal Holdings LLC (Francisco Partners Management LLC)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Peoples, Bruce E., Johnson, Michael R., Smith, Michael M.
• Primary Examiner(s): LU, KUEN S
• Application Number:
  US12/335,213
• Publication Number:
  US 20100153367A1
• Time in Patent Office: 1,786 Days
• Field of Search: 707/794, 707/803
• US Class Current: 707/794
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms

Abstract

In one embodiment, a method for determining concept attributes for a concept term includes receiving a concept term and determining one or more word senses for the concept term. A word sense is selected from the one or more word senses, and, based on the selected word sense, one or more conceptually similar terms for the concept term is determined. The method also includes determining that at least one of the one or more conceptually similar terms is a concept attribute for the concept term and generating a mapping to associate the concept attribute with the concept term. The mapping is stored in an onomasticon.

Claims

1. A computer-implemented method for determining concept attributes for a concept term, comprising:

receiving a concept term;

determining one or more word senses for the concept term;

selecting a word sense from the one or more word senses, the selected word sense indicating a particular semantic context of the concept term;

based on the selected word sense, determining one or more conceptually similar terms for the concept term;

determining whether each of the determined conceptually similar terms is within the particular semantic context of the concept term as indicated by the selected word sense, each of the conceptually similar terms that are determined to be within the particular semantic context of the concept term being a suitable concept attribute for the concept term;

generating a mapping to associate the suitable concept attributes with the concept term;

accessing an onomasticon, the onomasticon comprising a plurality of terms and a plurality of attributes associated with the plurality of terms; and

storing the mapping in the onomasticon.

2. The method of claim 1, further comprising:

receiving a second term; and

in response to receiving the second term, accessing the generated mapping stored in the onomasticon.

3. The method of claim 1, wherein receiving a concept term comprises:

identifying a concept term;

determining that an onomasticon contains no concept attributes associated with the concept term; and

selecting the concept term.

4. The method of claim 1, further comprising using a logic engine to determine that at least one of the one or more conceptually similar terms is a concept attribute for the concept term.

5. The method of claim 1, further comprising using an ontology to determine one or more word senses for the concept term.

6. The method of claim 1, wherein determining one or more conceptually similar terms for the concept term comprises identifying at least one hyponym, hypernym, holonyms, meronym, coordinate term, verb participle, troponym, or entailment for the concept term.

7. The method of claim 1, further comprising using a semantic reverse query expander to determine the one or more word senses for the concept term and determine the one or more conceptually similar terms for the concept term.

8. The method of claim 1, wherein the one or more conceptually similar terms comprises at least one foreign language term comprising a foreign language translation of a native language term conceptually similar to the concept term.

9. A system for determining concept attributes for a concept term comprising:

a memory; and

logic stored in a computer readable medium and when executed by a computer configured to;

receive a concept term;

determine one or more word senses for the concept term;

select a word sense from the one or more word senses, the selected word sense indicating a particular semantic context of the concept term;

based on the selected word sense, determine one or more conceptually similar terms for the concept term;

determine whether each of the determined conceptually similar terms is within the particular semantic context of the concept term as indicated by the selected word sense, each of the conceptually similar terms that are determined to be within the particular semantic context of the concept term being a suitable concept attribute for the concept term;

generate a mapping to associate the suitable concept attributes with the concept term;

access an onomasticon, the onomasticon comprising a plurality of terms and a plurality of attributes associated with the plurality of terms; and

store the mapping in the onomasticon.

10. The system of claim 9 wherein the logic, when executed by the computer, is further configured to:

receive a second term; and

in response to receiving the second term, access the generated mapping stored in the onomasticon.

11. The system of claim 9, wherein receiving a concept term comprises:

identifying a concept term;

determining that an onomasticon contains no concept attributes associated with the concept term; and

selecting the concept term.

12. The system of claim 9, the logic further configured to access a logic engine to determine that at least one of the one or more conceptually similar terms is a concept attribute for the concept term.

13. The system of claim 9, the logic further configured to access an ontology to determine one or more word senses for the concept term.

14. The system of claim 9, wherein determining one or more conceptually similar terms for the concept term comprises identifying at least one hyponym, hypernym, holonym, meronym, coordinate term, verb participle, troponym, or entailment for the concept term.

15. The system of claim 9, the logic further configured to access a semantic reverse query expander to determine the one or more word senses for the concept term and determine the one or more conceptually similar terms for the concept term.

16. The system of claim 9, wherein the one or more conceptually similar terms comprises at least one foreign language term comprising a foreign language translation of a native language term conceptually similar to the concept term.

17. A computer-implemented method for determining concept attributes for a concept type, comprising:

identifying a concept term;

determining one or more word senses for the concept term;

selecting a word sense from the one or more word senses, the selected word sense indicating a particular semantic context of the concept term;

based on the selected word sense, determining one or more conceptually similar terms for the concept term;

utilizing a logic engine to determine whether each of the determined conceptually similar terms is within the particular semantic context of the concept term as indicated by the selected word sense, each of the conceptually similar terms that are determined to be within the particular semantic context of the concept term being a suitable concept attribute for the concept term;

in response to determining whether each of the determined conceptually similar terms is a suitable concept attribute for the concept term, generating a mapping associating the suitable concept attributes with the concept term;

accessing an onomasticon, the onomasticon comprising a plurality of terms and a plurality of attributes associated with the plurality of terms;

storing the mapping in the onomasticon;

receiving a request to analyze a concept graph; and

accessing the generated mapping in response to the request.

18. The method of claim 17, wherein the one or more conceptually similar terms comprises at least one foreign language term comprising a foreign language translation of a native language term conceptually similar to the concept term.

19. A system for determining concept attributes for a concept term comprising:

a memory; and

logic stored in a computer readable medium and when executed by a computer configured to;

identify a concept term;

determine one or more word senses for the concept term;

select a word sense from the one or more word senses, the selected word sense indicating a particular semantic context of the concept term;

based on the selected word sense, determine one or more conceptually similar terms for the concept term;

access a logic engine to determine whether each of the determined conceptually similar terms is within the particular semantic context of the concept term as indicated by the selected word sense, each of the conceptually similar terms that are determined to be within the particular semantic context of the concept term being a suitable concept attribute for the concept term;

in response to determining whether each of the determined conceptually similar terms is a suitable concept attribute for the concept term, generate a mapping associating the suitable concept attributes with the concept term;

access an onomasticon, the onomasticon comprising a plurality of terms and a plurality of attributes associated with the plurality of terms;

store the mapping in the onomasticon;

receive a request to analyze a concept graph; and

access the generated mapping in response to the request.

20. The system of claim 19, wherein the one or more conceptually similar terms comprises at least one foreign language term comprising a foreign language translation of a native language term conceptually similar to the concept term.