Method and apparatus for detecting incorrectly translated text in a document

• US 8,296,124 B1
• Filed: 11/21/2008
• Issued: 10/23/2012
• Est. Priority Date: 11/21/2008
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Holsztynska, Joanna, Shaw, Hayden, Momoi, Katsuhiko, Beans, Erik, Khuong, Daniel
• Primary Examiner(s): Han, Qi
• Application Number:
  US12/276,049
• Time in Patent Office: 1,432 Days
• Field of Search: 704/2, 704/4, 704/5, 704/9, 704/7
• US Class Current: 704/2
• CPC Class Codes: G06F 40/51 Translation evaluation

Abstract

A system that detects incorrectly translated text in a document. During operation, the system determines a target language for the document. The system then identifies one or more terms in the document that are invalid terms for the language. Next, the system analyzes correlations between these invalid terms, and, based on these correlations, determines whether one or more of the invalid terms comprise incorrectly translated text.

Claims

1. A method for detecting incorrectly translated text in a translated document, comprising:

identifying a target language for the translated document;

identifying a set of one or more terms in the translated document that are invalid terms in the target language;

analyzing, as performed by a processor, the set of invalid terms to determine a distribution of invalid terms in the translated document; and

determining from the distribution of invalid terms whether one or more of the invalid terms comprise incorrectly translated text.

2. The method of claim 1, wherein identifying the set of invalid terms involves one or more of the following:

spell checking the target language to identify the set of invalid terms, or

using a language identification technique that identifies the set of invalid terms.

3. The method of claim 1, wherein identifying the target language for the translated document comprises:

receiving input from a user specifying the target language, or

using a language-identification technique to identify the target language.

4. The method of claim 1, further comprising:

receiving a list of one or more exception terms to exclude from the set of invalid terms;

identifying a particular one of the exception terms in the set of invalid terms; and

ignoring the identified particular exception term found in the list of invalid terms when analyzing the set of invalid terms.

5. The method of claim 1, wherein determining the distribution of invalid terms further comprises detecting contiguous invalid terms in the translated document.

6. The method of claim 5, further comprising identifying three or more contiguous invalid terms as a block of incorrectly translated text.

7. The method of claim 6, further comprising:

outputting the block of incorrectly translated text for confirmation by a user.

8. The method of claim 7, further comprising:

determining that the output block of incorrectly translated text was erroneously not translated during an automated translation process based on the confirmation.

9. The method of claim 8, further comprising:

determining a base language from which the translated document was translated; and

spell checking the base language to confirm that the block of incorrectly translated text is in the base language.

10. The method of claim 8, wherein receiving the translated document comprises:

using a web-crawler to determine one or more documents associated with an application; and

determining incorrectly translated text for the one or more documents associated with the application.

11. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for detecting incorrectly translated text in a translated document, the method comprising:

identifying a target language for the translated document;

identifying a set of one or more terms in the translated document that are invalid terms in the target language;

analyzing, as performed by the computer, the set of invalid terms to determine a distribution of invalid terms in the translated document; and

determining from the distribution of invalid terms whether one or more of the invalid terms comprise incorrectly translated text.

12. The non-transitory computer-readable storage medium of claim 11, wherein identifying the set of invalid terms involves one or more of the following:

using a spell-checker for the target language to identify the set of invalid terms, or

using a language identification technique that identifies the set of invalid terms.

13. The non-transitory computer-readable storage medium of claim 11, wherein identifying the target language for the translated document comprises:

receiving input from a user specifying the target language, or

using a language-identification technique to identify the target language.

14. The non-transitory computer-readable storage medium of claim 11, wherein the method further comprises:

receiving a list of one or more exception terms to exclude from the set of invalid terms;

identifying a particular one of the exception terms in the set of invalid terms; and

ignoring the identified particular exception term found in the list of invalid terms when analyzing the set of invalid terms.

15. The non-transitory computer-readable storage medium of claim 11, wherein determining the distribution of invalid terms further comprises detecting contiguous invalid terms in the translated document.

16. The non-transitory computer-readable storage medium of claim 15, the method further comprising identifying three or more contiguous invalid terms as a block of incorrectly translated text.

17. The non-transitory computer-readable storage medium of claim 16, the method further comprising outputting the block of incorrectly translated text for confirmation by a user.

18. The non-transitory computer-readable storage medium of claim 17, the method further comprising determining that the output block of incorrectly translated text was erroneously not translated during an automated translation process based on the confirmation.

19. The non-transitory computer-readable storage, medium of claim 18, wherein the method further comprises:

determining a base language from which the translated document was translated; and

using a spell-checker for the base language to confirm that the block of incorrectly translated text is in the base language.

20. A computing apparatus that detects incorrectly translated text in a translated document, comprising:

a processor and a memory;

a determining mechanism configured to identify a target language for the translated document;

an identification mechanism configured to identify a set of one or more terms in the translated document that are invalid terms in the target language; and

an analysis mechanism configured to analyze the set of invalid terms to determine a distribution of invalid terms in the translated document;

wherein the determining mechanism is further configured to determine from the distribution of invalid terms whether one or more of the invalid terms comprise incorrectly translated text.