AUTOMATED GLOSSARY CREATION

• US 20080243488A1
• Filed: 04/02/2007
• Published: 10/02/2008
• Est. Priority Date: 04/02/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cohen, Mitchell A., Byrd, Roy, Zeng, Sai, Balmelli, Laurent
• Granted Patent: US 7,945,438 B2
• Time in Patent Office: Days
• US Class Current: 704/10
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A method and device for creating a glossary includes a processor operable for executing computer instructions for identifying, in at least one information source, at least one glossary item identifying a part or a component, determining at least one glossary item form as a canonical form, defining, by using the canonical form, at least one syntactic structure, that includes one of the at least one identified glossary items, for each of at least one semantic classes, and searching a second information source for the at least one syntactic structure of the semantic class.

Claims

1. A computer-implemented method for creating a glossary, the method comprising:

identifying, in at least one information source, at least one glossary item identifying a part or a component;

determining at least one glossary item form as a canonical form;

defining, by using the canonical form, at least one syntactic structure, that includes one of the at least one identified glossary items, for each of at least one semantic classes; and

searching, in at least one of the at least one information source and a second information source, for the at least one syntactic structure of the semantic class.

2. The computer-implemented method according to claim 1, further comprising:

determining at least one glossary item form as a variant form;

defining, by using the variant form, at least one syntactic structure, that includes one of the at least one identified glossary items, for each of at least one semantic classes; and

searching, in at least one of the at least one information source and the second information source, for the at least one variant form of the syntactic structure of the semantic class.

3. The computer-implemented method according to claim 1, wherein the at least one semantic class is at least one of:

a symptom;

a cause; and

an action.

4. The computer-implemented method according to claim 1, wherein the determining is performed by mapping variant glossary item forms onto canonical forms.

5. The computer-implemented method according to claim 1, wherein the defining is performed by parsing to identify the at least one syntactic structure typical of a semantic class.

6. The computer-implemented method according to claim 1, further comprising:

defining, by using the canonical form of the glossary item, at least one syntactic structure, that does not include one of the at least one identified glossary items, for each of at least one semantic classes.

7. The computer-implemented method according to claim 1, further comprising:

assigning the at least one semantic class, including the identified syntactic structure, to at least one of the glossary items.

8. The computer-implemented method according to claim 7, further comprising:

using parsing rules to assign at least one additional semantic class to at least one of a phrase and a clause in at least one of;

the at least one information source; and

the second information source.

9. The computer-implemented method according to claim 1, wherein:

at least one of the at least one information source and the second information source is a failure report.

10. The computer-implemented method according to claim 1, wherein:

the searching is a lexical lookup for text in the second source.

11. A computer-implemented method for creating a glossary, the method comprising:

extracting, from at least one information source, text related to at least one of a part and a component;

identifying at least one of a part and a component in the text related to at least one of a part and a component;

determining, from the text related to at least one of a part and a component, a canonical form of a term related to at least one of a part and a component;

determining at least one variant form of the canonical form; and

storing the canonical form and the at least one variant form in a first glossary.

12. The computer-implemented method according to claim 11, further comprising:

extracting, from the at least one information source, text related to symptoms;

searching the text related to symptoms for at least one of the canonical form and the at least one variant form; and

identifying at least one symptom in the text related to symptoms.

13. The computer-implemented method according to claim 12, further comprising:

determining a canonical form of the symptom;

determining at least one variant form of the canonical form of the symptom; and

storing the canonical form of the symptom and the at least one variant form of the symptom in a second glossary.

14. The computer-implemented method according to claim 11, further comprising:

extracting, from the at least one information source, text related to causes;

searching the text related to causes for at least one of the canonical form and the at least one variant form; and

identifying at least one cause in the text related to causes.

15. The computer-implemented method according to claim 14, further comprising:

determining a canonical form of the cause;

determining at least one variant form of the canonical form of the cause; and

storing the canonical form of the cause and the at least one variant form of the cause in a second glossary.

16. The computer-implemented method according to claim 11, further comprising:

extracting, from the at least one information source, text related to actions;

searching the text related to actions for at least one of the canonical form and the at least one variant form; and

identifying at least one action in the text related to actions.

17. The computer-implemented method according to claim 16, further comprising:

determining a canonical form of the action;

determining at least one variant form of the canonical form of the action; and

storing the canonical form of the action and the at least one variant form of the action in a second glossary.

18. A device for creating a glossary, the method comprising:

a processor operable for executing computer instructions for;

identifying at least one glossary item in a first information source;

determining at least one glossary item form as a canonical form;

defining, by using the canonical form, at least one syntactic structure, that includes one of the at least one identified glossary items, for each of at least one semantic classes; and

searching, in at least one of the first information source and a second information source, for the at least one syntactic structure of the semantic class.

19. The device according to claim 18, wherein the processor is further operable for executing computer instructions for:

determining at least one glossary item form as a variant form; and

defining, by using the variant form, at least one syntactic structure, that includes one of the at least one identified glossary items, for each of at least one semantic classes.

20. The device according to claim 18, wherein the at least one glossary item is at least one of a component-noun word and a component-noun phrase.

21. A computer program product for creating a glossary, the computer program product comprising:

a storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising;

identifying, in at least one information source, at least one glossary item identifying a part or a component;

determining at least one glossary item form as a canonical form;

defining, by using the canonical form, at least one syntactic structure, that includes one of the at least one identified glossary items, for each of at least one semantic classes; and

searching, in at least one of the at least one information source and a second information source, for the at least one syntactic structure of the semantic class.

22. The computer program product according to claim 21, further comprising:

determining at least one glossary item form as a variant form;

defining, by using the variant form, at least one syntactic structure, that includes one of the at least one identified glossary items, for each of at least one semantic classes; and

searching, in at least one of the at least one information source and a second information source, for the at least one variant form of the syntactic structure of the semantic class.

23. The computer program product according to claim 21, wherein the at least one semantic class is at least one of:

a symptom;

a cause; and

an action.

24. The computer program product according to claim 21, wherein the determining is performed by mapping variant glossary item forms onto canonical forms.

25. The computer program product according to claim 21, wherein the defining is performed by parsing to identify the at least one syntactic structure typical of a semantic class.

26. The computer program product according to claim 21, further comprising:

defining, by using the canonical form of the glossary item, at least one syntactic structure, that does not include one of the at least one identified glossary items, for each of at least one semantic classes.

27. The computer program product according to claim 21, further comprising:

assigning the at least one semantic class, including the identified syntactic structure, to at least one of the glossary items.

28. The computer program product according to claim 27, further comprising:

using parsing rules to assign at least one additional semantic class to at least one of a phrase and a clause in the second information source.

29. The computer program product according to claim 21, wherein:

at least one of the first and second information source is a failure report.

30. The computer program product according to claim 29, wherein:

the searching is a lexical lookup for text in the failure report.