Methods and apparatus for understanding machine vocabulary

• US 7,869,989 B1
• Filed: 01/27/2006
• Issued: 01/11/2011
• Est. Priority Date: 01/28/2005
• Status: Expired due to Fees

• Current Assignee: Artificial Cognition Inc.
• Original Assignee: Artificial Cognition Inc.
• Inventors: Greenbaum, Donald R., Harvey, Charles D., Harvey, George H., Collins, Charles H.
• Primary Examiner(s): Wozniak; James S
• Assistant Examiner(s): Kovacek; David
• Application Number:
  US11/343,251
• Time in Patent Office: 1,810 Days
• Field of Search: 704 1- 10
• US Class Current: 704/9
• CPC Class Codes: G06F 40/242 Dictionaries

Abstract

Configurations herein provide a language processing mechanism operable to define a machine vocabulary and identify a machine language version of the words that preserves context and identifies the proper definition of the words by identifying and preserving context of a particular set of words, such as a sentence or paragraph. The machine vocabulary includes a definition section for each definition of a word. Each definition section includes a set of one or more definition elements. The definition elements include a predetermined format of definition fields, and each has a corresponding mask indicative of significant definition fields. The set of definition elements corresponding to a particular definition describe the usage of the word in a context matching that particular definition. Each definition element captures a characteristic of the definition according to fuzzy logic such that the definition elements collectively capture the context.

Claims

1. A method for representing text in a language independent format of multiple bits and fields of bits comprising:

referencing a word from a set of words into a dictionary of representations of words, in said format of multiple bits and fields of bits, to find a corresponding dictionary term, the set of words derived from a natural language usage defining a natural language context of the words in the set of words;

mapping the referenced dictionary term to at least one definition element indicative of usage of the word in at least one context, the definition elements defining a record of fields;

comparing the mapped definition element to the corresponding fields in the definition elements of other words in the set of words, the comparison operative to identify similar contexts between the definition elements;

disambiguating the referenced words by analyzing each of the definition elements of the referenced words with the definition elements of the other referenced words, the analysis operable to determine a particular definition for each of the referenced words in the context of the set of words, disambiguating including;

performing, with a processor, bitwise operations on at least a subset of the fields in the definition elements with corresponding fields in the other definition elements in the set of words, each of the definition elements indicative of a particular context, the operations for identifying a particular definition element based on the context in the set of words, the definition elements including bit fields of class, method, and category in the high bits, the method field determining a structure of fields in lower order bits, wherein disambiguating is performed on definition elements of equal category and method fields; and

identifying, from the comparing, a definition element corresponding to the usage of the word in a context of the set of words.

2. The method of claim 1 wherein the set of words is in series and referencing includes parsing each word from the series of words, further comprising:

comparing the parsed words to the dictionary, the dictionary indicative of definitions of the parsed words in a field structured format defined by the definition elements, each word having at least one definition element, the definitions corresponding to different contexts of the parsed words.

3. The method of claim 1 wherein performing operations includes performing bitwise operations on the definition elements, the definition elements having fields operable by the bitwise operations, wherein the operations further include selectively masking particular fields and result in identifying dissimilar bits between definition elements.

4. The method of claim 1 wherein performing operations includes performing bitwise operations on the definition elements, the definition elements including bits ranging from most significant to least significant, the definition elements having fields operable by the bitwise operations, wherein the operations result in identifying dissimilar bits between definition elements.

5. The method of claim 4 further comprising, for each definition element:

defining a mask selectively indicative of an applicable subset of bits of the definition element for a particular definition of the word; and

including the defined mask in the operation of the corresponding definition element, the mask operable to indicate applicable bits of the definition element for the particular definition context, the bitwise operations including one or more logical operations with the mask for nulling inapplicable bits.

6. The method of claim 1 wherein each of the definition elements identifies a particular definition of a word in the context defined by proximate words, each definition element having a context specific definition.

7. The method of claim 6 wherein the definition elements further comprise word lists populated with values defining a bitwise representation that is employed in computations with other definition elements to identify similar contexts in which the words are used.

8. The method of claim 1 wherein the record fields of the definition elements are bit fields, and the comparing includes rules which perform a bitwise operation on particular fields, the operations including XOR between the definition elements and ANDs between the masks of each definition element.

9. The method of claim 1 wherein the record of fields in the definition elements defines an ordered significance to the fields, the most significant bits in the definition element defining the most significant fields.

10. The method of claim 9 wherein the fields of the definition elements include a class field defining the most significant bits, the class defining a title of a list of words from among other classes of words.

11. The method of claim 10 wherein the fields of the definition elements include a method field indicative of the sizes of bit fields for the less significant bits, the method field occupying the lower two bits in the class field in an overlay manner, the class and category filed configured to concatenate to a foundation field, the foundation field being an index of classification into a root word list, the method field defining the structure for less significant fields.

12. The method of claim 10 wherein disambiguating is for determining a degree of difference between words, further comprising:

identifying words having the same values in the class and method fields;

performing an XOR on the definition elements of the identified words;

parsing a result of the XOR to identify the most significant bit; and

identifying the bit field containing the most significant bit to determine the difference between the identified words.

13. The method of claim 1 wherein disambiguating is for determining a subset relation between words, further comprising:

determining the bit mask value from the definition elements;

performing a logical AND on the determined bit mask values;

computing a comparison result of the performed logical AND;

mapping the comparison result back to the definition elements to find a match; and

concluding that a subset relation exists if the mapped comparison result equals the definition element of the superset, each word having a single corresponding definition element for the meaning in context.

14. The method of claim 13 further comprising computing a definition of a word from a plurality of the subset relations comprising:

determining compatible subsets of the word by identifying common values in at least one field defined by the highest bits the compatible subsets;

accumulating an accumulated word by iteratively performing a logical OR on the definition element of the word and the definition element of the subset;

storing the result of each performed logical OR in the accumulated word for each of the determined compatible subsets; and

identifying the value of the accumulated word as defined by the subsets employed as the accumulated subsets.

15. The method of claim 1 wherein disambiguating is for determining a relative closeness in meaning, further comprising

determining, from the definition elements, the bit mask value of each of a base word and words for comparison;

performing, for each of the words for comparison, an XOR on the bit mask value of the base word and the word for comparison to generate a closeness value;

comparing the closeness values corresponding to each of the words for comparison; and

concluding that the lowest closeness value identifies which of the words for comparison has the closest meaning to the base word.

16. The method of claim 1 further comprising a plurality of definition elements, each word having one definition element with a primary definition element value and at least one definition element with a multiple taxonomy value, the multiple taxonomy value indicative of different contexts of usage for the word, the primary definition element denoted by a predetermined value in a field of the definition element.

17. The method of claim 1 wherein disambiguating is for translating a definition of multiple words though the bitwise operations, further comprising:

identifying the definition element of a first word and a second word for which a translated definition is sought;

performing an XOR on the definition elements of the first and second words to generate a definition value; and

mapping the definition value to find a matching definition element, the matching definition element corresponding to the definition element of the translated definition.

18. The method of claim 1 wherein a result of the bitwise operation equals the definition element of another word describing the usage in context.

19. A method for processing language elements comprising:

receiving a series of words in a natural language;

parsing the series of words to derive an ordered set of words in the natural language, the set of words derived from a natural language usage defining a natural language context of the words in the set of words;

mapping each of the parsed words to a corresponding term in a dictionary of representations of multiple bits and fields of bits, of words in the particular natural language;

mapping each of the identified dictionary terms to at least one definition element, the definition elements defining a record of fields and indicative of the word in context with other words;

processing the mapped definition elements with corresponding fields in the other mapped definition elements from the ordered set of words to identify corresponding contexts of words in the ordered set of words, each of the definition elements identifying a particular definition of a word in the context defined by proximate words, each definition element having a context specific definition;

disambiguating the parsed words by analyzing each of the definition elements of the parsed words with the definition elements of the other parsed words, the analysis operable to determine a particular definition for each of the parsed words in a context of the series of words, disambiguating including;

performing, with a processor, bitwise operations on at least a subset of the fields in the definition elements with corresponding fields in the other definition elements in the word sequence, each of the definition elements indicative of a particular context, the operations for identifying a particular definition element based on the context in the word sequence, the definition elements including bit fields of class, method, and category in the high bits, the method field determining a structure of fields in lower order bits, wherein disambiguating is performed on definition elements of equal category and method fields; and

identifying, from the processing, a particular definition element for each of the words applicable to the word in the ordered set of words.

20. The method of claim 19 wherein the at least one definition element further comprises a plurality of definition elements, each of the definition elements corresponding to a mask indicative of significant fields in the definition elements, further comprising:

a primary definition element indicative of a deterministic usage of the word; and

at least one secondary definition element indicative of particular contextual usages of the word applicable to the primary definition.

21. The method of claim 20 wherein the mapped dictionary term further maps to at least one definition section, each definition section corresponding to a primary definition of the word having at least one definition element.

22. The method of claim 21 wherein comparison results in an indication of the most significant bit different from another definition element, the location of the most significant bit that differs indicative of the difference in meaning between the words corresponding to the definition elements.

23. The method of claim 21 wherein comparison results in an indication of dissimilar fields between the compared elements, the comparison indicative of a common context of a manner in which the words are related.

24. A data processing device for representing text in a language independent format of multiple bits and fields of bits, comprising:

a processor operable to execute instructions;

a memory responsive to the processor operable to store the instructions;

an interface operable to transfer data between a user device, the processor and the memory, the instructions operable to;

reference a word from a set of words into a dictionary of bitwise representations of words to find a corresponding dictionary term, the set of words derived from a natural language usage defining a natural language context of the words in the set of words;

map the referenced dictionary term to at least one definition element indicative of usage of the word in a specific context, the definition elements defining a record of fields, each of the definition elements identifying a particular definition of a word in the context defined by proximate words, each definition element having a context specific definition;

compare the mapped definition element to the corresponding fields in the definition elements of other words in the set of words, the comparison operative to identify similar contexts between the definition elements;

disambiguate the referenced words by analyzing each of the definition elements of the referenced words with the definition elements of the other referenced words, the analysis operable to determine a particular definition for each of the referenced words in a context of the series of words, disambiguating including;

performing bitwise operations on at least a subset of the fields in the definition elements with corresponding fields in the other definition elements in the set of words, each of the definition elements indicative of a particular context, the operations for identifying a particular definition element based on the context in the set of words, the definition element including bit fields of class, method, and category in the high bits, the method field determining a structure of fields in lower order bits, wherein disambiguating is performed on definition elements of equal category and method fields; and

identify, from the comparing, a definition element corresponding to the usage of the word in a context of the set of words.

25. A computer program product having a non-transitory computer readable medium operable to store computer program logic embodied in computer program code encoded thereon for processing language elements comprising:

computer program code for receiving a series of words in a natural language;

computer program code for parsing the series of words to derive an ordered set of words in the natural language, the set of words derived from a natural language usage defining a natural language context of the words in the set of words;

computer program code for mapping each of the parsed words to a corresponding term in a dictionary of bitwise representations of words in the particular natural language;

computer program code for mapping each of the identified dictionary terms to at least one definition element, the definition elements indicative of the word in context with other words, each of the definition elements defining a record of fields and identifying a particular definition of a word in the context defined by proximate words, each definition element having a context specific definition;

computer program code for processing the mapped definition elements with corresponding fields in the other mapped definition elements from the ordered set of words to identify corresponding contexts of words in the ordered set of words;

computer program code for identifying, from the processing, a particular definition element for each of the words applicable to the word in the ordered set of words;

computer program code for comparing the referenced words to the dictionary, the dictionary indicative of definitions of the referenced words, each word having at least one definition, the definitions corresponding to different contexts of the referenced words; and

computer program code for disambiguating the referenced words by analyzing each of the definition elements of the referenced words with the definition elements of the other referenced words, the analysis operable to determine a particular definition for each of the referenced words in a context of the set of words,

disambiguating including;

performing bitwise operations on at least a subset of the fields in the definition elements with corresponding fields in the other definition elements in the word sequence, each of the definition elements indicative of a particular context, the operations for identifying a particular definition element based on the context in the set of words, the definition element including bit fields of class, method, and category in the high bits, the method field determining a structure of fields in lower order bits, wherein disambiguating is performed on definition elements of equal category and method fields; and

computer program code for identifying, from the comparing, a particular definition element for each of the words applicable to the word in the ordered set of words.

26. A machine vocabulary processor for translation independent of a native natural language comprising:

means for generating a bitwise language representation by classifying language elements according to a predetermined set of rules, the bitwise language representation having a plurality of bitwise definition elements corresponding to words in a particular usage context;

means for parsing the words to identify the definition elements, each of the definition elements having fields;

means for receiving a natural language sentence in a first natural language, the natural language sentence comprising a series of words, the series of words derived from a natural language usage defining a natural language context of the words in the set of words;

means for disambiguating the referenced words by analyzing each of the definition elements of the referenced words with the definition elements of the other referenced words, the analysis operable to determine a particular definition for each of the referenced words in the context of the series of words, disambiguating including;

performing bitwise operations on at least a subset of the fields in the definition elements with corresponding fields in the other definition elements in the set of words, each of the definition elements indicative of a particular context, the operations for identifying a particular definition element based on the context in the set of words, the definition element includes bit fields of class, method, and category in the high bits, the method field determining a structure of fields in lower order bits, wherein disambiguating is performed on definition elements of equal category and method fields;

means for computing a series of definition elements corresponding to each of the words in the first natural language sentence, the definition elements indicative of each of the words in the context of the received natural language sentence; and

means for determining, from the computed series of definition elements, a second set of language elements in a second natural language, the definition elements selected in a manner that preserves the specific context from the first natural language sentence, each of the definition elements identifying a particular definition of a word in the context defined by proximate words, each definition element having a context specific definition.