Method, used by computers, for developing an ontology from a text in natural language

• US 8,417,512 B2
• Filed: 09/18/2007
• Issued: 04/09/2013
• Est. Priority Date: 09/19/2006
• Status: Expired due to Fees

• Current Assignee: Alcatel-Lucent SA (Nokia Corporation)
• Original Assignee: Alcatel-Lucent SA (Nokia Corporation)
• Inventors: Larvet, Phillippe
• Primary Examiner(s): Han, Qi
• Application Number:
  US11/857,420
• Publication Number:
  US 20080071521A1
• Time in Patent Office: 2,030 Days
• Field of Search: 704/9, 704/1, 704/10, 704/7, 704/257
• US Class Current: 704/9
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

The invention relates to a method, used by computers, for developing an ontology (70) of a text (10) in natural language, comprising the steps of:

• • receiving text data from the text (10);
  • extracting the syntax and meaningful words (20) from the text via a grammatical analysis (S100) of the received data;
  • for each of at least some of the meaningful words (20) of the text: searching (S200) for a definition (40) of that word (20) by means of at least one electronic dictionary (30, 35), extracting the syntax and the meaningful words of that definition, and creating (S300) an elementary lexical graph (50) of that definition based on the syntax and the meaningful words of that definition; and
  • merging (S400) at least two of the elementary lexical graphs (50) created, as a function of the syntax of the text, so as to create at least one semantic graph (60) of the text.

The invention further concerns a computer program product and an electronic data processing system comprising code means adapted to implement the steps of the method of the invention.

Claims

1. A computer implemented method for developing an ontology (70) of a text (10) in natural language, comprising the steps of:

receiving text data from text (10);

a grammatical analyzer extracting, by a computer, syntax and meaningful words (20) from the text via a grammatical analysis (S100) of the received text data;

for each of at least some of the meaningful words (20) of the text;

searching (S200) for a definition (40) of the meaningful word (20) by means of at least one electronic dictionary (30, 35), the grammatical analyzer extracting syntax and meaningful words of the definition, and creating (S300) an elementary lexical graph (50) of the definition based on the syntax and the meaningful words of the definition; and

merging (S400), by the computer, at least two of the elementary lexical graphs (50) created, as a function of the syntax of the text, so as to create at least one semantic graph (60) of the text.

2. The method according to claim 1, further comprising a step, before the merging step (S400), of extracting relations between the meaningful words of the text based on the syntax and the meaningful words of the text that have been extracted via the grammatical analysis, the merging step being based on these relations between meaningful words of the text.

3. The method according to claim 1, wherein:

the extraction first step further comprises the extraction via the grammatical analysis (S100) of a grammatical structure of the text, said structure comprising one or more grammatical groups; and

the merging step (S400) is further based on extracted grammatical groups, so as to create at least one semantic graph (60) for each of said one or more extracted grammatical groups.

4. The method according to claim 1, further comprising a step, for each meaningful word of the text, of searching for synonyms (45) of that word and a definition of those synonyms by means of said at least one dictionary (35);

and

the merging step (S400) is further effected as a function of the definitions of the synonyms.

5. The method according to claim 4, further comprising a step, before the merging step, of

classifying the synonyms found for each meaningful word as a function of the definitions of that meaningful word and its synonyms;

and wherein;

the merging step is further effected as a function of a result of the classification of the synonyms.

6. The method according to claim 1, further comprising a step (S500):

of eliminating components not linked to said at least one semantic graph (60) that has been created.

7. The method according to claim 1, wherein each of the steps (S100-S400), apart from the step of reception of the text data, is effected “

on the fly”

, after the step of reception of the text data.

8. The method according to claim 1, wherein said at least one semantic graph (70) is formalized in a language based on XML.

9. The method according to claim 8 wherein the language is Web Onology Language OWL.

10. The method according to claim 8 wherein the language is Resource Description Framework RDF.

11. The method according to claim 1, wherein the text data corresponds to a text of a service enquiry (10).

12. The method according to claim 1 further comprising searching for a Web service as a function of the at least one semantic graph (60).

13. The method according to claim 1 wherein the computer is an electronic data processing tool.

14. Electronic data processing tool adapted to develop an ontology of a text in a natural language comprising:

a computer having code means adapted to;

receive text data from text;

extract the syntax and meaningful words from the text via a grammatical analysis of the received text data;

for each of at least some of the meaningful words of the text search for a definition by means of at least one electronic dictionary, extract a syntax and meaningful words of the definition, and create an elementary lexical graph of the definition based on the syntax and the meaningful words of the definition; and

merge at least two of the elementary lexical graphs created, as a function of the syntax of the text, so as to create at least one semantic graph of the text.

15. Electronic data processing tool adapted to develop an ontology of a text in a natural language comprising:

means for receiving text data from text;

means for extracting the syntax and meaningful words from the text via a grammatical analysis of the received text data;

means for searching for a definition for each of at least some of the meaningful words by means of at least one electronic dictionary;

means for extracting a syntax and meaningful words of the definition;

means for creating an elementary lexical graph of the definition based on the syntax and the meaningful words of the definition; and

means for merging at least two of the elementary lexical graphs created, as a function of the syntax of the text, so as to create at least one semantic graph of the text.