MACHINE TRANSLATION SPLIT BETWEEN FRONT END AND BACK END PROCESSORS

• US 20120179450A1
• Filed: 03/01/2012
• Published: 07/12/2012
• Est. Priority Date: 05/01/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Menezes, Arul A., Quirk, Christopher B., Rashid, Richard F., Moore, Robert C.
• Granted Patent: US 8,886,516 B2
• Time in Patent Office: Days
• US Class Current: 704/2
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

A method of translation includes uploading a source text portion to a back end processor. The back end processor identifies a subset of translation knowledge associated with the source text portion. The back end processor downloads the subset to a front end processor. A translation engine runs on the front end processor. The translation engine generates a translation of the source text portion as a function of the subset.

Claims

1. A method of supporting translation, comprising:

receiving a source text portion to be translated;

splitting the source text portion into minimal independent translation segments;

identifying, for each minimal independent translation segment, a corresponding knowledge statement;

assembling the identified knowledge segments together to form a subset of translation knowledge; and

remotely transmitting the subset of translation knowledge so that it can be utilized to support a translation of the source text portion of a function of the subset.

2. The method of claim 1, wherein identifying comprises limiting the subset to a limited number of words and phrases.

3. The method of claim 1, wherein identifying comprises limiting the subset to words and phrases identified as being potentially in the source text portion.

4. The method of claim 1, wherein receiving comprises receipt by a back end service provider.

5. The method of claim 1, wherein receiving comprises receipt by a web service provider.

6. The method of claim 1, wherein receiving comprises receipt by a computer cluster.

7. The method of claim 1, wherein receiving the source text comprises receiving portions of the source text that are divided from one another.

8. (canceled)

9. The method of claim 8, wherein each translation knowledge subset is specifically associated with one of the plurality of source text portions.

10. The method of claim 8, wherein running the translation engine comprises applying each translation knowledge subset to its corresponding one of the plurality of source text portions.

11. The method of claim 8, wherein running the translation engine comprises utilizing the translation engine to apply each translation knowledge subset to its corresponding one of the plurality of source text portions.

8-1. A method of translation, comprising:

receiving a translation knowledge subset for each of a plurality of source text portions; and

running a translation engine upon each of the source text portions as a function of the corresponding translation knowledge subset.

12. A computer-implemented method, comprising:

obtaining a collection of source text split into minimal independent translation segments;

identifying, for each minimal independent translation segment, a corresponding knowledge statement; and

remotely transmitting the corresponding knowledge statements.

13. The method of claim 12, wherein said steps of obtaining, identifying and remotely transmitting are carried out by a back end processor.

14. The method of claim 13, wherein the backend processor comprises a web service provider.

15. The method of claim 13, wherein the back end processor comprises a computing cluster.

16. The method of claim 13, wherein the minimal independent translation segments are selected based upon a set of predetermined selection criteria.

17. The method of claim 13, wherein obtaining comprises obtaining minimal independent translation segments that are constrained to a limited number of words and/or phrases.

18. The method of claim 13, wherein obtaining comprises obtaining minimal independent translation segments that are determined to be likely included in the source text.

19. The method of claim 13, wherein identifying comprises choosing words and phrases determined to correspond to the source text portion.

20. The method of claim 13, wherein the minimal independent translation segments are selected based on the source text and a set of qualifying criteria.