Relational database method and systems for alphabet based language representation

• US 8,738,353 B2
• Filed: 09/05/2007
• Issued: 05/27/2014
• Est. Priority Date: 09/05/2007
• Status: Active Grant

• Current Assignee: Modibo Soumare
• Original Assignee: Modibo Soumare
• Inventors: Soumare, Modibo
• Primary Examiner(s): He, Jialong
• Application Number:
  US11/899,223
• Publication Number:
  US 20090063131A1
• Time in Patent Office: 2,456 Days
• Field of Search: 704 1- 10
• US Class Current: 704/1
• 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 of representing a language statement having one or more words includes capturing an expression of the language statement, associating one or more properties with each of the one or more words in the language statement, substantially removing as necessary one or more first ambiguities in the language statement, establishing one or more functional roles for each of the one or more words in the language statement, processing as necessary one or more second ambiguities in the language statement, and providing a representation of the language statement including the one or more properties associated with and the one or more functional roles established for each of the one or more words, the one or more first ambiguities substantially removed, and the one or more second ambiguities processed.

Claims

1. A method of representing a language statement having one or more words, the method comprising:

capturing an expression of the language statement in a digital database;

electronically associating each word in the language statement with at least one word database record from the digital database, the word database record having a plurality of properties including person, gender, tense, part of speech, and semantic word classification;

substantially removing with a computer any first ambiguities as to which word database record corresponds to each word in the language statement;

establishing one or more functional roles for each word in the language statement, wherein the functional roles are categories comprising at least one of complement-object-indirect, complement-object-direct, determinative-complement, noun-attribute, noun-complement, orphan-attribute, orphan-noun, orphan-verb, subject, verb, and verb-attribute, and the functional roles are determined by the context of the words within the language statement, and by the properties of the word database record associated with the word in the language statement;

processing any second ambiguities in the language statement with a computer, using the functional roles and the properties, the second ambiguities selected from a group of ambiguities comprising functional, semantic, and grammatical incongruities between the words in the language statement; and

providing a representation of the language statement as database records, the representation including the properties of the word database records associated with each word in the language statement, and the functional roles established for each word in the language statement, and wherein which the first ambiguities are substantially removed, and the second ambiguities are processed.

2. The method of claim 1, wherein capturing an expression of the language statement in digital memory comprises:

ending the language statement by adding a statement end identifier;

processing with a digital database stored procedure one or more non-alphanumeric characters included in the language statement;

separating one or more sentences included in the language statement; and

deducing a source language type for the language statement.

3. The method of claim 2, wherein deducing a source language type for the language statement comprises:

identifying a language type for each of the one or more words in the language statement; and

assigning a source language type to the language statement by checking language type continuity between one or more words in the language statement.

4. The method of claim 1, wherein electronically associating word in the language statement with at least one word database record comprises:

identifying at least one match for each word in the language statement with a word database record from the digital database.

5. The method of claim 1, wherein substantially removing first ambiguities comprises:

separating one or more sentences included in the language statement; and

processing one or more idioms in each of the one or more sentences based on word proximity, functional role, and classification property.

6. The method of claim 5, wherein processing one or more idioms in each of the one or more sentences based on word proximity, functional role, and classification property comprises:

identifying one or more idioms in each of the one or more sentences based on word proximity, functional role, and classification property; and

transforming the one or more idioms identified into one or more non-idiomatic phrases or words.

7. The method of claim 6, wherein the one or more idioms identified are selected from a group of idioms comprising semantic idioms, grammatical idioms, and phrasal verbs.

8. The method of claim 1, wherein establishing one or more functional roles for each word in the language statement comprises:

separating sentences included in the language statement;

assigning one or more functional roles to each word in each sentence of the language statement; and

generating a functional representation of the language statement, the functional representation comprising the properties of each word database record corresponding to a word in each sentence, and the functional roles of each word in each of sentence.

9. The method of claim 1, wherein establishing the one or more functional roles further comprises analyzing the relative proximity of each word in the language statement.

10. The method of claim 1, wherein processing any second ambiguities in the language statement comprises:

separating sentences included in the language statement;

establishing functional relationships where appropriate between two or more words in the sentences, or between two or more of the sentences in the language statement;

identifying the one or more second ambiguities between the two or more words in the sentences, or between two or more of the sentences in the language statement; and

substantially removing at least one of the second ambiguities.

11. The method of claim 10, wherein substantially removing at least one of the second ambiguities comprises substantially removing at least one noun- complement or determinative-complement ambiguity.

12. The method of claim 11, wherein substantially removing at least one noun-complement or determinative-complement ambiguity comprises:

identifying at least one noun complemented by at least one noun-complement or determinative-complement;

checking for semantic congruence between the at least one noun complemented and the at least one noun-complement or determinative-complement; and

replacing one or more properties of the noun complemented by the at least one noun-complement or determinative-complement.

13. The method of claim 1 further comprising:

associating each word database record with an expression in a natural language; and

translating the language statement into the natural language by outputting the expressions corresponding to the representation of the language statement.

14. The method of claim 1 further comprising:

searching one or more records for one or more portions of the language statement representation; and

providing an output based on the search of the one or more records for one or more portions of the language statement representation.

15. A system for representing one or more language statements each including one or more words, the system comprising:

at least one computer including one or more software components configured to;

capture an expression of a language statement in a database;

associate words in the language statement with word database records having a plurality of properties including person, gender, tense, part of speech, and semantic classification;

substantially remove as necessary one or more first ambiguities in the language statement as to which word database record corresponds to each word in the language statement;

establish one or more functional roles for each of the one or more words in the language statement, wherein the functional roles are categories comprising at least one of complement-object-indirect, complement-object-direct, determinative-complement, noun-attribute, noun-complement, orphan-attribute, orphan-noun, orphan-verb, subject, verb, and verb-attribute, and the functional roles are determined by the context of each word within the language statement, and by the properties of the word database record associated with each word in the language statement;

identify as necessary one or more second ambiguities in the language statement using the functional roles and the properties, wherein the second ambiguities selected from a group of ambiguities comprising functional, semantic, and grammatical incongruities between the words in the language statement; and

provide a representation of the language statement as database records, the representation including the properties of the word database records associated with each word in the language statement, and the functional roles for established for each of the one or more words, wherein the first ambiguities are substantially removed, and the second ambiguities are identified.

16. The system of claim 15, wherein associating one or more properties with each of the one or more words in the language statement comprises:

identifying at least one match for each word in the language statement with a word database record from a database.

17. The system of claim 15, wherein substantially removing as necessary one or more first ambiguities in the language statement comprises:

separating one or more sentences included in the language statement; and

processing one or more idioms in each of the one or more sentences based on word proximity, functional role, and classification property.

18. The system of claim 17, wherein processing one or more idioms in each of the one or more sentences based on word proximity, functional role, and classification comprises:

identifying one or more idioms in each of the one or more sentences based on word proximity, functional role, and classification; and

transforming the one or more idioms identified into one or more non-idiomatic phrases or words.

19. The system of claim 15, wherein establishing one or more functional roles for each of the one or more words in the language statement comprises:

separating sentences included in the language statement;

assigning one or more functional roles to each word in each sentence of the language statement; and

generating a functional representation of the language statement, the functional representation comprising the properties of each word database record corresponding to a word in each sentence, and the functional roles of each word in each of sentence.

20. The system of claim 15, wherein identifying as necessary one or more second ambiguities in the language statement comprises:

separating sentences included in the language statement;

establishing functional relationships where appropriate between two or more words in the sentences, or between two or more of the sentences in the language statement;

identifying the one or more second ambiguities between the two or more words in the sentences, or between two or more of the sentences in the language statement; and

substantially removing at least one of the one or more second ambiguities.

21. A system for representing one or more language statements each including at least one word, the system comprising:

a computer including a software component configured to;

capture an expression of a language statement;

associate each word in the language statement with at least one word database record having a plurality of properties including person, gender, tense, part of speech, and semantic classification;

substantially remove ambiguities as to which word database record corresponds to each word in the language statement;

establish a functional role for each word in the language statement based on the context of each word within the language statement, and the properties of the word database record associated with each word in the language statement, the functional role comprising at least one context dependent category selected from the group comprising complement-object-indirect, complement-object-direct, determinative-complement, noun-attribute, noun-complement, orphan-attribute, orphan-noun, orphan-verb, subject, verb, and verb-attribute;

identify further ambiguities in the language statement, as necessary, using the functional roles and the properties, wherein the second ambiguities are selected from a group comprising functional, grammatical, and semantic incongruities between the words in the language statement; and

provide a representation of the language statement as database records, the representation including the functional roles for each word in the language statement, and the properties of the word database records associated with each word in the languages statement.