Systems and methods for enhancing machine translation post edit review processes

• US 8,886,515 B2
• Filed: 10/19/2011
• Issued: 11/11/2014
• Est. Priority Date: 10/19/2011
• Status: Active Grant

• Current Assignee: SDL Inc (RWS Holdings Plc)
• Original Assignee: Language Weaver, Inc. (RWS Holdings Plc)
• Inventors: Van Assche, Gert
• Primary Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US13/277,149
• Publication Number:
  US 20130103381A1
• Time in Patent Office: 1,119 Days
• Field of Search: 704/2, 704/3, 704/4, 704/5, 704/8, 704/9, 704/10
• US Class Current: 704/2
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory

Abstract

Systems and methods for enhancing machine translation post edit review processes are provided herein. According to some embodiments, methods for displaying confidence estimations for machine translated segments of a source document may include executing instructions stored in memory, the instructions being executed by a processor to calculate a confidence estimation for a machine translated segment of a source document, compare the confidence estimation for the machine translated segment to one or more benchmark values, associate the machine translated segment with a color based upon the confidence estimation for the machine translated segment relative to the one or more benchmark values, and provide the machine translated segment having the color in a graphical format, to a client device.

Claims

1. A method for displaying confidence estimations for machine translated segments of a source document, the method comprising:

executing instructions stored in memory, the instructions being executed by a processor to;

calculate a confidence estimation for a machine translated segment of the source document;

compare the confidence estimation for the machine translated segment to one or more benchmark values;

associate the machine translated segment with a color based upon the confidence estimation for the machine translated segment relative to the one or more benchmark values; and

provide the machine translated segment having the color in a graphical format, to a client device.

2. The method according to claim 1, wherein the machine translated segment includes a subunit of the machine translated segment, the subunit of the machine translated segment including a string of characters from the machine translated segment.

3. The method according to claim 2, wherein comparison of the confidence estimation to the one or more benchmark values is utilized to generate an estimated translation complexity for the machine translated segment.

4. The method according to claim 3, wherein executing instructions stored in memory further comprises the instructions being executed by a processor to provide the machine translated segment to a client device, the machine translated segment including subunits that each have a color associated therewith.

5. The method according to claim 1, wherein executing instructions stored in memory further comprises the instructions being executed by a processor to display a translation unit that includes source content of the document from which the machine translated segment was created, along with the machine translated segment.

6. The method according to claim 1, wherein the graphical format includes a pie chart having one or more wedges, each wedge including an aggregate number of machine translated segments that include the same color.

7. The method according to claim 1, wherein machine translated segments with confidence estimations that meet or exceed a first benchmark value are associated with a first color, and machine translated segments with confidence estimations that meet or exceed a second benchmark value are associated with a second color.

8. The method according to claim 7, wherein the first benchmark value has a magnitude that is less than a magnitude of the second benchmark value.

9. The method according to claim 1, wherein the one or more benchmark values includes a plurality of benchmark values, each of the plurality of benchmark values being associated with a unique color, each of the plurality of benchmark values having different magnitude from the other benchmark values.

10. The method according to claim 1, further comprising:

calculate a confidence estimation for a post edited segment, the post edited segment including a machine translated segment that has been post edited by a post edit reviewer;

compare the confidence estimation for the post edited segment to one or more benchmark values; and

associate the post edited segment with an updated color based upon the confidence estimation for the post edited segment relative to the one or more benchmark values.

11. The method according to claim 10, further comprising providing, via a user interface, the post edited segment having the updated color along with the machine translated segment having an original color, the difference between the updated color and the original color indicating a change in estimated translation complexity between the machine translated segment and the post edited segment.

12. A system for displaying confidence estimations for machine translated segments of a source document, the system comprising:

a memory for storing executable instructions;

a processor for executing the instructions, the instructions including;

a confidence estimator module that calculates a confidence estimation for a machine translated segment of a source document;

an analysis module that compares the confidence estimation for the machine translated segment to one or more benchmark values and associates the machine translated segment with a color based upon the confidence estimation for the machine translated segment relative to the one or more benchmark values; and

an interface module that provides the machine translated segment having the color in a graphical format, to a client device.

13. The system according to claim 12, wherein the machine translated segment includes a subunit of the machine translated segment, the subunit of the machine translated segment including a string of characters from the machine translated segment.

14. The system according to claim 13, wherein the interface module displays the subunits in order relative to the machine translated segment.

15. The system according to claim 14, wherein the interface module provides the machine translated segment to a client device, the machine translated segment including subunits that each have a color associated therewith.

16. The system according to claim 12, wherein the interface module displays a translation unit that includes source content of the document from which the machine translated segment was created, along with the machine translated segment.

17. The system according to claim 12, wherein the interface module generates a graphical representation that includes a pie chart having one or more wedges, each wedge including an aggregate number of machine translated segments that include the same color.

18. The system according to claim 12, wherein the analysis module associates machine translated segments with confidence estimations that meet or exceed a first benchmark value with a first color, and associates machine translated segments with confidence estimations that meet or exceed a second benchmark with a second color.

19. The system according to claim 18, wherein the first benchmark value has a magnitude that is less than a magnitude of the second benchmark value.

20. The system according to claim 12, wherein the analysis module utilizes a plurality of benchmark values, each of the plurality of benchmark values being associated with a unique color, each of the plurality of benchmark values having different magnitude from the other benchmark values.

21. A non-transitory computer readable storage medium having a program embodied thereon, the program being executable by a processor to perform a method for displaying confidence estimations for machine translated segments of a source document, the method comprising:

executing instructions stored in memory, the instructions being executed by a processor to;

calculate a confidence estimation for a machine translated segment of a source document;

compare the confidence estimation for the machine translated segment to one or more benchmark values;

associate the machine translated segment with a color based upon the confidence estimation for the machine translated segment relative to the one or more benchmark values; and

provide the machine translated segment having the color in a graphical format, to a client device.