Shao O Chin

US Patent:

7016895, Mar 21, 2006

Filed:

Feb 25, 2003

Appl. No.:

10/374877

Inventors:

Peter J. Dehlinger - Palo Alto CA, US
Shao Chin - Santa Cruz CA, US

Assignee:

Word Data Corp. - Palo Alto CA

International Classification:

G06F 17/30
G06F 7/00

US Classification:

707 5, 707 3, 707 4, 704 7, 704 9

Abstract:

Disclosed are a computer-readable code, system and method for classifying a target document in the form of a digitally encoded natural-language text as belonging to one or more of two or more different classes. Each of a plurality of non-generic words and optionally, words groups characterizing the target document is selected as a descriptive term if the term has an above-threshold selectivity value in at least one library of texts in a field, where the selectivity value of a term is a measure of the field-specificity of that term. There is then determined, for each of the plurality of sample texts having associated classification identifiers, a match score related to the number of descriptive terms present in or derived from that text that match those in the target text. From the selected matched texts, and the associated classification identifiers, a classification determination of the target document is made.

US Patent:

7024408, Apr 4, 2006

Filed:

Jul 1, 2003

Appl. No.:

10/612644

Inventors:

Peter J. Dehlinger - Palo Alto CA, US
Shao Chin - Santa Cruz CA, US

Assignee:

Word Data Corp. - Palo Alto CA

International Classification:

G06F 17/30

US Classification:

707 5, 707 6, 704 7, 704 9

Abstract:

Disclosed are a computer-readable code, system and method for classifying a target document in the form of a digitally encoded natural-language text as belonging to one or more of two or more different classes. For each of a plurality of non-generic words and/or words groups characterizing the target document, there is determined a selectivity value calculated as the frequency of occurrence of that term in a library of texts in one field, relative to the frequency of occurrence of the same term in one or more other libraries of texts in one or more other fields, respectively, and the document is represented as a vector of terms, where the coefficient assigned to each term is a function of the selectivity value determined for that term. There is then determined, for each of the plurality of sample texts having associated classification identifiers, a match score related to the number of descriptive terms present in or derived from that text that match those in the target text. From the selected matched texts, and the associated classification identifiers, a classification determination of the target document is made.

US Patent:

7181451, Feb 20, 2007

Filed:

Sep 30, 2002

Appl. No.:

10/261971

Inventors:

Peter J. Dehlinger - Palo Alto CA, US
Shao Chin - Stanford CA, US

Assignee:

Word Data Corp. - Palo Alto CA

International Classification:

G06F 17/30
G06F 7/00
G06F 17/28
G06F 17/00

US Classification:

707 6, 707 1, 707200, 704 4, 704 9, 715531, 715534

Abstract:

Disclosed is an automated system, machine-readable storage medium embodying computer-executable code, and method for generating descriptive words and optionally, multi-word groups derived from a digitally encoded, natural-language input text that describes a concept, invention, or event in a selected field. The system includes (a) an electronic digital computer, (b) a database of words and optionally, word-groups derived from a plurality of texts, and (c) machine-readable storage medium embodying computer-executable code for accessing the database. The database provides, or can be used to calculate, a selectivity value for each of the words and optionally, word groups contained in or derived from the input text. Words and optionally, word groups having an above-threshold selectivity value are selected as descriptive terms from the input text.

US Patent:

7386442, Jun 10, 2008

Filed:

Jul 1, 2003

Appl. No.:

10/612732

Inventors:

Peter J. Dehlinger - Palo Alto CA, US
Shao Chin - Santa Cruz CA, US

Assignee:

Word Data Corp. - Palo Alto CA

International Classification:

G06F 7/00
G06F 17/20
G06F 17/21
G06F 17/27

US Classification:

704 10, 704 7, 704 9, 707 3, 707 4, 707 5, 707 6

Abstract:

A computer method, system and code, for representing a natural-language document in a vector form suitable for text manipulation operations are disclosed. The method involves determining (a) for each of a plurality of terms selected from one of (i) non-generic words in the document, (ii) proximately arranged word groups in the document, and (iii) a combination of (i) and (ii), a selectivity value of the term related to the frequency of occurrence of that term in a library of texts in one field, relative to the frequency of occurrence of the same term in one or more other libraries of texts in one or more other fields, respectively. The document is represented as a vector of terms, where the coefficient assigned to each term includes a function of the selectivity value determined for that term.

US Patent:

20040006459, Jan 8, 2004

Filed:

Sep 30, 2002

Appl. No.:

10/261970

Inventors:

Peter Dehlinger - Palo Alto CA, US
Shao Chin - Stanford CA, US

International Classification:

G06F017/27

US Classification:

704/010000

Abstract:

Disclosed are a computer-readable code, system and method for comparing a target concept, invention, or event with each of a plurality of texts. Each of a plurality of non-generic words and optionally, words groups characterizing the target concept, invention, or event, is selected as a descriptive term if the term has an above-threshold selectivity value in at least one library of texts in a field, where the selectivity value of a term is a measure of the field-specificity of that term. There is then determined, for each of the plurality of texts, a match score related to the number of descriptive terms present in or derived from that text that match those in the target concept, invention, or event. Texts having the highest match scores are selected.

US Patent:

20040006547, Jan 8, 2004

Filed:

Sep 30, 2002

Appl. No.:

10/262192

Inventors:

Peter Dehlinger - Palo Alto CA, US
Shao Chin - Stanford CA, US

International Classification:

G06F007/00

US Classification:

707/001000

Abstract:

Disclosed is a computer-accessible database composed of a list of non-generic words contained in a plurality of digitally encoded texts. Associated with each term is a selectivity value or values that are related to the frequency of occurrence of that word in at least one library of texts in a field, relative to the frequency of occurrence of the same word in one or more libraries of texts in one or more other fields, respectively. Also associated with each term are one or more text identifiers identifying one or more of the digitally processed texts containing that word. Each text identifier may be further associated with sentence and word-number identifiers that identify the sentence and word number(s) of a given database word.

US Patent:

20040054520, Mar 18, 2004

Filed:

Jul 1, 2003

Appl. No.:

10/612739

Inventors:

Peter Dehlinger - Palo Alto CA, US
Shao Chin - Santa Cruz CA, US

International Classification:

G06F017/28

US Classification:

704/005000

Abstract:

Disclosed are a computer-readable code, system and method for comparing a target concept, invention, or event with each of a plurality of texts. Each of a plurality of non-generic words and optionally, words groups characterizing the target concept, invention, or event, is selected as a vector term if the term has an above-threshold selectivity value in at least one library of texts in a field, where the selectivity value of a term is a measure of the field-specificity of that term. There is then determined, for each of the plurality of texts, a match score related to the number of vector terms present in or derived from that text that match those in the target concept, invention, or event. Texts having the highest match scores are selected.

US Patent:

20040064304, Apr 1, 2004

Filed:

May 15, 2003

Appl. No.:

10/438486

Inventors:

Peter Dehlinger - Palo Alto CA, US
Shao Chin - Santa Cruz CA, US

Assignee:

WORD DATA CORP - Palo Alto CA

International Classification:

G06F017/27

US Classification:

704/009000

Abstract:

A computer method for representing a natural-language document in a vector form suitable for text manipulation operations is disclosed. The method involves determining (a) for each of a plurality of terms composed of non-generic words and, optionally, proximately arranged word groups in the document, a selectivity value of the term related to the frequency of occurrence of that term in a library of texts in one field, relative to the frequency of occurrence of the same term in one or more other libraries of texts in one or more other fields, respectively. The document is represented as a vector of terms, where the coefficient assigned to each term includes a function of the selectivity value determined for that term, and optionally related to the inverse document frequency of that word in one or more libraries of texts. Also disclosed are a computer-readable code for carrying out the method, a computer system that employs the code, and a vector produced by the method.