Systems and methods for automatically estimating a translation time including preparation time in addition to the translation itself

• US 9,128,929 B2
• Filed: 01/14/2011
• Issued: 09/08/2015
• Est. Priority Date: 01/14/2011
• Status: Active Grant

• Current Assignee: SDL Ltd.
• Original Assignee: SDL Language Technologies
• Inventors: Albat, Thomas Fritz
• Primary Examiner(s): Kazeminezhad, Farzad
• Application Number:
  US13/007,460
• Publication Number:
  US 20120185235A1
• Time in Patent Office: 1,698 Days
• Field of Search: 704/2, 704/3, 704/8, 704/277
• US Class Current: 1/1
• 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
• CPC Class Codes: G06Q 10/063118 Staff planning in a project environment

Abstract

A method for automatically estimating a translation time comprises receiving translation data, determining one or more translation parameters based on the translation data, retrieving one or more pre-determined translation coefficients associated with the one or more translation parameters, calculating an estimated translation time based on the one more or more translation parameters and the one or more pre-determined translation coefficients, and a base time to prepare the translation in addition to the translation itself. The method may further comprise reporting the estimated translation time to a user, receiving, from the user, a request to perform a translation associated with the translation data, performing the translation, recording an actual translation time, comparing the actual translation time to the estimated translation time, and based on the comparison, revising the one or more pre-determined translation coefficients to improve the estimating of the translation time.

Claims

1. A method for automatically estimating a translation time, the method comprising:

receiving translation data including content to be translated;

determining translation parameters based on the translation data, the translation parameters comprising a task time which provides a base time that is used for additional time to prepare for work in addition to actual translation itself, a band percentage that defines a recognized percentage of the content that has been previously translated, and a content type that defines a subject matter which is indicative of a complexity of the content;

retrieving one or more pre-determined translation coefficients associated with at least one of the translation parameters, the estimated translation time calculated at least in part based on the one or more pre-determined translation coefficients; and

executing a module by a processor, the module stored in memory, the executed module configured to calculate an estimated translation time for translating the content using the translation parameters and the one or more pre-determined translation coefficients.

2. The method of claim 1, further comprising:

reporting the estimated translation time to a user;

receiving, from the user, a request to perform a translation associated with the translation data;

performing the translation;

recording an actual translation time;

comparing the actual translation time to the estimated translation time; and

based on the comparison, revising the one or more pre-determined translation coefficients to improve the estimating of the translation time.

3. The method of claim 1, wherein the translation parameters include one or more of the following:

a base task time, a target language, a number of words in a translation source, and a number of pages in the translation source.

4. The method of claim 1, wherein the translation data includes one or more of the following:

a source file, a translation memory, a suggestion dictionary, and a reference file.

5. The method of claim 1, wherein a value of a translation coefficient is based on historical importance of a translation parameter associated with the translation coefficient in calculating of the estimated translation time.

6. The method according to claim 1, further comprising splitting a word count parameter into match bands, wherein each of the match bands is associated with a portion of the translation data, further wherein a match band comprises a likelihood that a translation of the portion of the translation data will be correct, the match band being expressed as a percentage.

7. A system for automatically estimating a translation time, the system comprising:

a communication module stored in memory and executed by a processor to receive translation data including content to be translated and to retrieve one or more pre-determined translation coefficients associated with translation parameters, the translation parameters comprising a task time which provides a base time that is used for additional time to prepare for work in addition to actual translation itself, a band percentage that defines a recognized percentage of the content that has been previously translated, and a content type that defines a subject matter which is indicative of a complexity of the content; and

a processing module stored in memory and executed by a processor to determine the translation parameters based on the translation data and to calculate an estimated translation time using the translation parameters and the one or more pre-determined translation coefficients.

8. The system of claim 7, further comprising:

a reporting module to report the estimated translation time to a user, wherein the communication module is to receive, from the user, a request to perform a translation associated with the translation data;

a translation module to perform the translation;

a time recording module to record an actual translation time;

a comparing module to compare the actual translation time to the estimated translation time; and

a coefficient adjusting module to revise the one or more pre-determined translation coefficients based on the comparison.

9. The system of claim 7, wherein the translation is a computer-aided translation.

10. The system of claim 7, wherein the translation parameters include one or more of the following:

a base task time, a target language, a number of words in a translation source, and a number of pages in the translation source.

11. The system of claim 7, wherein the translation data includes one or more of the following:

a source file, a translation memory, a suggestion dictionary, and a reference file.

12. The system of claim 7, wherein a value of a translation coefficient is based on historical importance of a translation parameter associated with the translation coefficient in calculating of the estimated translation time.

13. A non-transitory computer readable storage medium having embodied thereon a program, the program being executable by a processor to perform a method for translating content, the method comprising:

receiving translation data including content to be translated;

determining translation parameters based on the translation data, the translation parameters comprising a task time which provides a base time that is used for additional time to prepare for work in addition to actual translation itself, a band percentage that defines a recognized percentage of the content that has been previously translated, and a content type that defines a subject matter which is indicative of a complexity of the content; and

calculating an estimated translation time for translating the content using the translation parameters and one or more pre-determined translation coefficients.

14. The non-transitory computer readable storage medium of claim 13, further comprising:

retrieving the one or more pre-determined translation coefficients associated with the translation parameters.

15. The non-transitory computer readable storage medium of claim 13, further comprising:

reporting the estimated translation time to a user;

receiving, from the user, a request to perform a translation associated with the translation data;

performing the translation;

recording an actual translation time;

comparing the actual translation time to the estimated translation time; and

based on the comparison, revising the one or more pre-determined translation coefficients to improve the estimating of the translation time.

16. The non-transitory computer readable storage medium of claim 13, wherein the translation parameters include one or more of the following:

a base task time, a target language, a number of words in a translation source, and a number of pages in the translation source.

17. A method for automatically estimating a translation time, the method comprising:

receiving translation data including content to be translated;

determining translation parameters based on the translation data, the translation parameters comprising a task time which provides a base time that is used for additional time to prepare for work in addition to actual translation itself, a band percentage that defines a recognized percentage of the content that has been previously translated, and a content type that defines a subject matter which is indicative of a complexity of the content;

splitting a word count parameter into match bands, wherein each of the match bands is associated with a portion of the translation data;

retrieving one or more pre-determined translation coefficients associated with at least one of the translation parameters, the estimated translation time calculated at least in part based on the one or more pre-determined translation coefficients; and

executing a module by a processor, the module stored in memory, the executed module configured to calculate an estimated translation time for translating the content using the translation parameters and the one or more pre-determined translation coefficients.