Key term extraction

• US 20070022115A1
• Filed: 07/21/2005
• Published: 01/25/2007
• Est. Priority Date: 07/21/2005
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bernth, Arendse, Walters, David, McCord, Michael, Warburton, Kara
• Granted Patent: US 7,478,092 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/36 Creation of semantic tools, e.g. ontology or thesauri
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99937 Sorting

Abstract

An improved solution for extracting and identifying key terms in content is provided. In the solution, one or more documents can be obtained and one or more candidate terms can be obtained from the content of each document. Subsequently, one or more exclusion conditions can be used to filter the candidate terms thereby generating a set of key terms. In particular, all common terms and/or all near duplicate candidate terms can be excluded from the set of key terms. The set of key terms can be used in translating the content, generating a glossary/index for the content, detecting and/or correcting incorrect terms and usages of terms in the content, building a terminology repository, and/or the like. In one embodiment, the key term extraction is performed to facilitate the translation of product documentation into a second language in order to release the product in one or more nations. In this case, candidate terms that have already been translated into the second language can also be excluded from the key terms.

Claims

1. A method of managing content, the method comprising:

obtaining a set of candidate terms from the content; and

filtering the set of candidate terms based on a set of general exclusion conditions, wherein the set of general exclusion conditions includes at least one of;

an exclusion condition for excluding all candidate terms that appear in a set of common terms or an exclusion condition for excluding all near duplicate candidate terms.

2. The method of claim 1, further comprising:

identifying a set of unknown terms in the content;

receiving a correction to one of the set of unknown terms; and

incorporating the correction into the content.

3. The method of claim 1, further comprising:

translating the filtered set of candidate terms; and

providing the translated set of candidate terms and the content for use by a translator.

4. The method of claim 3, wherein the filtering is further based on at least one of:

a set of language-specific exclusion conditions or a set of product-specific exclusion conditions.

5. The method of claim 1, further comprising generating at least one of:

a glossary, a terminology repository, or an index for the content based on the filtered set of candidate terms.

6. A program product stored on a computer-readable medium, which when executed, enables a computer infrastructure to manage the translation of content, the program product comprising program code for performing the method steps of claim 1.

7. A method of generating a system for managing the translation of content, the method comprising:

obtaining a computer infrastructure; and

for each of the steps of claim 1, deploying a means for performing the step to the computer infrastructure.

8. A system for managing content, the system comprising:

a system for obtaining a set of candidate terms from the content; and

a system for filtering the set of candidate terms based on a set of general exclusion conditions, wherein the set of general exclusion conditions includes at least one of;

an exclusion condition for excluding all candidate terms that appear in a set of common terms or an exclusion condition for excluding all near duplicate candidate terms.

9. The system of claim 8, further comprising:

a system for identifying a set of unknown terms in the content;

a system for receiving a correction to one of the set of unknown terms; and

a system for incorporating the correction into the content.

10. The system of claim 8, further comprising:

a system for translating the filtered set, of candidate terms; and

a system for providing the translated set of candidate terms and the content for use by a translator.

11. The system of claim 10, wherein the filtering is further based on at least one of:

a set of language-specific exclusion conditions or a set of product-specific exclusion conditions.

12. The system of claim 8, further comprising a system for generating at least one of:

a glossary, a terminology repository, or an index for the content based on the filtered set of candidate terms.

13. A method of managing the translation of content, the method comprising:

obtaining a set of candidate terms from the content for translation from a source language to a target language;

obtaining a set of general exclusion conditions, wherein the set of general exclusion conditions includes at least one of;

an exclusion condition for excluding all candidate terms that appear in a set of common terms or an exclusion condition for excluding all near duplicate candidate terms;

filtering the set of candidate terms based on the set of general exclusion conditions;

translating the filtered set of candidate terms; and

providing the translated set of candidate terms and the content for use by a translator.

14. The method of claim 13, further comprising identifying a set of unknown terms in the content.

15. The method of claim 13, further comprising obtaining a set of language-specific exclusion conditions based on the target language, wherein the filtering step is further based on the set of language-specific exclusion conditions, and wherein the set of language-specific exclusion conditions includes an exclusion condition for excluding each candidate term that has previously been translated to the target language.

16. The method of claim 13, further comprising obtaining a set of product-specific exclusion conditions, wherein the content is associated with a product and wherein the filtering step is further based on the set of product-specific exclusion conditions.

19. The system of claim 13, wherein the filtering is further based on a set of language-specific exclusion conditions, and wherein the set of language-specific exclusion conditions includes an exclusion condition for excluding each candidate term that has previously been translated to the target language.

20. The system of claim 13, wherein the content is associated with a product and wherein the filtering step is further based on a set of product-specific exclusion conditions.

17. A system for managing the translation of content, the system comprising:

a system for obtaining a set of candidate terms from the content for translation from a source language to a target language;

a system for filtering the set of candidate terms based on a set of general exclusion conditions, wherein the set of general exclusion conditions includes at least one of;

an exclusion condition for excluding all candidate terms that appear in a set of common terms or an exclusion condition for excluding all near duplicate candidate terms;

a system for translating the filtered set of candidate terms; and

a system for providing the translated set of candidate terms and the content for use by a translator.

18. The system of claim 17, further comprising a system for identifying a set of unknown terms in the content.