Data security system for natural language translation

Patent metadata

Field	Value
Publication number	US-9317501-B2
Application number	US-201514656078-A
Country	US
Kind code	B2
Filing date	Mar 12, 2015
Priority date	Nov 30, 2010
Publication date	Apr 19, 2016
Grant date	Apr 19, 2016

Abstract

A method, computer system, and computer program product for translating information. The computer system receives the information for a translation. The computer system identifies portions of the information based on a set of rules for security for the information in response to receiving the information. The computer system sends the portions of the information to a plurality of translation systems. In response to receiving translation results from the plurality of translation systems for respective portions of the information, the computer system combines the translation results for the respective portions to form a consolidated translation of the information.

First claim

What is claimed is:

1. A method for translating a natural-language text document, the method comprising:
a computer system receiving the natural-language text document for translation;
the computer system dividing each of a plurality of sentences in the document into a plurality of portions based on a set of rules that specify how to divide up each of the plurality of sentences based on content of the plurality of sentences;
the computer system translating the portions of each of the plurality of sentences to form initially translated first portions, using a translation engine;
the computer system sending the initially translated first portions to a plurality of respective, human translators, for correction, wherein none of the plurality of human translators is sent any of the plurality of translated sentences in its entirety; and
responsive to receiving translation corrections from the plurality of human translators for the initially translated first portions, the computer system combining the translations for the respective portions with the translation corrections received from the plurality of human translators to form consolidated translations for each of the plurality of sentences, and updating at least one model used by the translation engine based on the translation corrections received from the plurality of human translators.

2. The method of claim 1 , further comprising:
the computer system removing user data from the natural-language text document based on the set of rules prior to sending the initially translated first portions to the plurality of human translators.

3. The method of claim 1 , wherein the plurality of human translators are determined, by the computer system, based on a rule for geographically separating the plurality of human translators.

4. The method of claim 1 , wherein the step of the computer system sending the initially translated first portions to the plurality of human translators, comprises:
the computer system detecting a presence of potential human translators at translation systems; and
the computer system using the presence of the potential human translators detected from the translation systems to determine the plurality of human translators based on a plurality of rules.

5. The method of claim 1 , wherein the portions of each of the plurality of sentences in the natural-language text document are phrases, wherein metadata is associated with each portion of the plurality of portions that identify a sequence of the each portion.

6. The method of claim 1 , wherein a requestor requests the translation of the natural-language text document and further comprising:
the computer system sending the consolidated translations of the plurality of sentences to the requestor.

7. The method of claim 1 , wherein the natural-language text document comprises at least one of text, voice, an audio recording, a document, and video.

8. The method of claim 1 , wherein the natural-language text document is encrypted.

9. A computer system for translating a natural-language text document, the computer system comprising:
a CPU, a computer-readable storage device, and a computer-readable memory; first program instructions to receive the natural-language text document for translation;
second program instructions to divide each of a plurality of sentences in the document into a plurality of portions based on a set of rules that specify how to divide up each of the plurality of sentences based on content of the plurality of sentences;
third program instructions to translate the portions of each of the plurality of sentences to form initially translated first portions, using a translation engine;
fourth program instructions to send the initially translated first portions to a plurality of human translators, for correction, wherein none of the plurality of human translators is sent any of the plurality of translated sentences in its entirety; and
fifth program instructions to combine the translations for the respective portions with corrections received from the plurality of human translators to form consolidated translations for each of the plurality of sentences in response to receiving the translation corrections from the plurality of human translators for the initially translated first portions, and update at least one model used by the translation engine based on the corrections received from the plurality of human translators, wherein the first program instructions, the second program instructions, the third program instructions, the fourth program instructions, and the fifth program instructions are stored on the computer-readable storage device and executed by the CPU via the computer-readable memory.

10. The computer system of claim 9 , further comprising:
sixth program instructions to remove user data from the natural-language text document based on the set of rules prior to sending the initially translated first portions to the plurality of human translators, wherein the sixth program instructions are stored on the computer-readable storage device and executed by the CPU via the computer-readable memory.

11. The computer system of claim 9 , wherein the fourth program instructions to send the initially translated first portions to the plurality of respective, human translators, include program instructions to determine the plurality of respective, human translators, based on a rule for geographically separating the plurality of human translators.

12. The computer system of claim 9 , wherein the fourth program instructions to send the initially translated first portions to the plurality of respective, human translators, comprise:
program instructions to detect a presence of the potential human translators at translation systems; and
program instructions to use the presence of the potential human translators detected from the translation systems to determine the plurality of human translators based on a plurality of rules.

13. The computer system of claim 9 , wherein the portions of each of the plurality of sentences in the natural-language text document are phrases, wherein metadata is associated with each portion of the plurality of portions that identify a sequence of the each portion.

14. The computer system of claim 9 , wherein a requestor requests the translation of the natural-language text document and further comprising:
sixth program instructions to send the consolidated translations of the plurality of sentences to the requestor, wherein the sixth program instructions are stored on the computer-readable storage device and executed by the CPU via the computer-readable memory.

15. The computer system of claim 9 , wherein the natural-language text document is encrypted and comprises at least one of text, voice, an audio recording, a document, and video.

16. A computer-readable storage device having computer-readable program instructions stored on the computer-readable storage device, wherein the computer-readable program instructions are executed by a CPU to translate a natural-language text document, wherein the computer-readable program instructions comprise:
computer-readable program instructions for receiving the natural-language text document for translation;
computer-readable program instructions for dividing each of a plurality of sentences in the document into a plurality of portions based on a set of rules that specify how to divide up each of the plurality of sentences based on content of the plurality of sentences;
computer-readable program instructions for translating the portions of each of the plurality of sentences to form initially transl

Assignees

• IBM

Inventors

• Kraenzel Carl J
• Lubensky David M
• Mandalia Baiju Dhirajlal
• Wu Cheng

Classifications

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L13/02

  Methods for producing synthetic speech; Speech synthesisers · CPC title

• G06F40/58 Primary

  Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation · CPC title

• G06F40/51 Primary

  Translation evaluation · CPC title

• G06F17/2854

  Physics · mapped topic