Method, system, and appartus for selecting an acronym expansion

• US 9,213,690 B2
• Filed: 04/29/2010
• Issued: 12/15/2015
• Est. Priority Date: 04/29/2010
• Status: Expired due to Fees

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Feng, Shicong, Xiong, Yuhong, Yao, Conglei, Liu, Wei
• Primary Examiner(s): Pullias, Jesse
• Application Number:
  US13/695,238
• Publication Number:
  US 20130110500A1
• Time in Patent Office: 2,056 Days
• Field of Search: 704/1, 704/9, 704/10
• US Class Current: 1/1
• CPC Class Codes: G06F 40/16 Automatic learning of transformation rules, e.g. from examples
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

According to one embodiment of the present invention, there is provided a method of selecting an expansion for an acronym in a document of a set of linked documents. The method comprises obtaining for each occurrence of the acronym in the set of linked documents one or more possible acronym expansions and an associated probability that the one or more possible acronym expansions is the correct acronym expansion. The further comprises identifying a sub-set of documents from the set of linked documents in which the acronym occurs. The method further comprises recalculating the associated probabilities for a first occurrence of an acronym in the sub-set of documents based, in part, on the associated probabilities of other occurrences of the acronym in the sub-set of documents and the distance between the first occurrence and the other occurrences.

Claims

1. A method of selecting an expansion for an acronym in a document of a set of linked documents, the method comprising:

obtaining for each occurrence of the acronym in the set of linked documents one or more possible acronym expansions and an associated probability that the one or more possible acronym expansions is the correct acronym expansion;

identifying a sub-set of documents from the set of linked documents in which the acronym occurs;

recalculating the associated probabilities for a first occurrence of an acronym in the sub-set of documents based, in part, on the associated probabilities of other occurrences of the acronym in the sub-set of documents and the distance between the first occurrence and the other occurrences;

normalizing the recalculated associated probabilities for the first occurrence such that the sum of the recalculated associated probabilities equals one; and

iteratively recalculating the associated probabilities for the first occurrence of the acronym using any previously recalculated associated probabilities of the other occurrences of the acronym.

2. The method of claim 1, further comprising, recalculating the associated probabilities for the other occurrences of the acronym using any previously recalculated associated probabilities.

3. The method of claim 2, further comprising iteratively recalculating a predetermined number of times the associated probabilities for all of the occurrences of the acronym, each time using the previously recalculated associated probabilities.

4. The method of claim 1, further comprising, selecting the acronym expansion having the highest recalculated probability as the correct acronym expansion.

5. The method of claim 4, further comprising modifying the document in which the first occurrence of acronym occurs to include the selected acronym expansion.

6. The method of claim 1, wherein the distance is the minimum number of links required to navigate from a document comprising the first occurrence and a document comprising a different occurrence of the same acronym.

7. The method of claim 1, wherein each document is a web page, and wherein the set of documents is a web site.

8. The method of claim 1, wherein the step of recalculating the associated probabilities for the first occurrence of the acronym further comprises performing the equation:

9. The method of claim 1, wherein the step of obtaining comprises obtaining the probabilities using a content-based analysis technique.

10. The method of claim 1, further comprising iteratively recalculating a predetermined number of times the associated probabilities for all of the occurrences of the acronym until each ambiguous acronym converges to a stable result.

16. The method of claim 1, further comprising, recalculating the associated probabilities for the other occurrences of the acronym using any previously normalized recalculated associated probabilities.

17. The method of claim 16, further comprising iteratively recalculating a predetermined number of times the associated probabilities for all of the occurrences of the acronym, each time using the previously normalized recalculated associated probabilities.

18. The method of claim 17, wherein the predetermined number of times is based on at least one of available processing power and time available.

11. A computing device, comprising:

a processor,

a memory in communication with the processor, and

computer executable instructions stored in the memory and executable on the processor to determine an acronym expansion of an acronym in a web page of a web site by;

obtaining, through a content-based analysis, for each occurrence of the acronym in the web site, one or more possible acronym expansions and an associated probability that the one or more acronym expansions is the correct acronym expansion;

identifying a set of web pages from the web site in which the acronym occurs;

calculating a new set of probabilities for a first occurrence of the acronym in the identified set of web pages, the calculation being made in part based on the associated probabilities of other occurrences of the acronym in other ones of the set of web pages and the number of links linking the other ones of the set of web pages;

normalizing the new set of probabilities for the first occurrence such that the sum of the recalculated associated probabilities equals one; and

iteratively recalculating the associated probabilities for the first occurrence of the acronym using any previously recalculated associated probabilities of the other occurrences of the acronym.

12. The computing device of claim 11, further comprising iteratively recalculating at least 50 times the associated probabilities for all of the occurrences of the acronym, each time using the previously normalized recalculated associated probabilities.

13. The computing device of claim 11, further comprising computer executable instructions stored in the memory and executable on the processor to determine an acronym expansion of an acronym in a web page of a website by modifying the document in which the first occurrence of acronym occurs to include the selected acronym expansion.

14. The computing device of claim 11, further comprising computer executable instructions stored in the memory and executable on the processor to determine an acronym expansion of an acronym in a web page of a website by selecting the acronym expansion having the highest recalculated probability as the correct acronym expansion.

15. A non-transitory machine-readable storage carrying computer-implementable instructions that, when interpreted by a computer, cause the computer to:

obtain for each occurrence of the acronym in the set of linked documents one or more possible acronym expansions and an associated probability that the one or more possible acronym expansions is the correct acronym expansion;

identify a sub-set of documents from the set of linked documents in which the acronym occurs;

recalculate the associated probabilities for a first occurrence of an acronym in the sub-set of documents based, in part, on the associated probabilities of other occurrences of the acronym in the sub-set of documents and the distance between the first occurrence and the other occurrences;

normalize the recalculated associated probabilities for the first occurrence such that the sum of the recalculated associated probabilities equals one; and

iteratively recalculate the associated probabilities for the first occurrence of the acronym using any previously recalculated associated probabilities of the other occurrences of the acronym.

19. The machine-readable storage of claim 15, further comprising computer-implementable instructions that, when interpreted by a computer, cause the computer to display the identified acronym expansion when a user selects the acronym.

20. The machine-readable storage of claim 15, further comprising computer-implementable instructions that, when interpreted by a computer, cause the computer to insert the acronym expansion into the web page in which the acronym occurs.