Computer-implemented method, computer software and apparatus for use in a translation system

• US 8,521,506 B2
• Filed: 09/21/2006
• Issued: 08/27/2013
• Est. Priority Date: 09/21/2006
• Status: Active Grant

• Current Assignee: SDL Ltd.
• Original Assignee: SDL PLC (RWS Holdings Plc)
• Inventors: Lancaster, Mark, Gordon, Alastair, Mills, Keith
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US11/525,231
• Publication Number:
  US 20080077395A1
• Time in Patent Office: 2,532 Days
• Field of Search: None
• US Class Current: 704/2
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory
• 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 computer-implemented method for use in natural language translation comprises performing in software processes, the steps of: comparing source material with stored material in a first natural language, said stored material having previously been translated from said first natural language to at least a second natural language, identifying at least a part of said source material which has a relationship with at least a part of said stored material, outputting said identified part of source material and said identified part of stored material in a form suitable for review by a user, and replacing said identified part of source material with said identified part of stored material to assist full translation of said source material from said first natural language to at least said second natural language.

Claims

1. A computer-implemented method for use in natural language translation, said method being performed by a computer system including memory and processing circuitry programmed to execute a set of software processes, the steps of:

a) comparing, by the processing circuitry, source material with stored material in a first natural language, said stored material being retrieved from a database stored in the memory and having previously been translated from said first natural language to at least a second natural language;

b) identifying, by the processing circuitry, a part of said source material which has a relationship in said first natural language with at least a part of said stored material;

c) comparing said source material with forbidden terminology material;

d) outputting, by the processing circuitry in said first natural language, said identified part of source material and said identified part of stored material in a form suitable for review by a user; and

e) replacing said identified part of source material with said identified part of stored material in said first natural language to assist in subsequent full translation of said source material from said first natural language to at least said second natural language.

2. A method according to claim 1, wherein said replacing is carried out in response to input from said user.

3. A method according to claim 1, performed in support of a separate process of conducting full translation of said source material from said first natural language to at least said second natural language with reference to said stored material which has previously been translated into at least said second natural language.

4. A method according to claim 3, wherein said conducting full translation of said source material from said first natural language to at least said second natural language comprises a human translator translating parts of said source material which were not identified as having a relationship with parts of said stored material.

5. A method according to claim 3, wherein said conducting full translation of said source material from said first natural language to at least said second natural language comprises a machine translation process performed by the computer system, the machine translation process translating parts of said source material which were not identified as having a relationship with parts of said stored material.

6. A method according to claim 3, wherein said conducting full translation of said source material from said first natural language to at least said second natural language comprises a human translator and a machine translation process performed by the computer system, the human translator and machine translation process together translating parts of said source material which were not identified as having a relationship with parts of said stored material.

7. A method according to claim 3, comprising outputting said full translation of said source material in a form suitable for review by a user.

8. A method according to claim 7, wherein parts of said source material which were translated with reference to said stored material which had previously been translated into at least said second natural language, parts of said source material which were translated by a human translator and parts of said source material which were translated by a machine translation process are outputted in different forms.

9. A method according to claim 8, wherein said different forms comprise different colours.

10. A method according to claim 1, wherein said stored material comprises at least one translation memory.

11. A method according to claim 10, wherein said at least one translation memory contains a plurality of stored segment pairs, each of said stored segment pairs comprising source material in said first natural language and corresponding translation in at least said second natural language.

12. A method according to claim 11, wherein each of said stored segments pairs corresponds to at least one of:

a paragraph,

a sentence, and

a phrase.

13. A method according to claim 1, further comprising the step of dividing said source material into a plurality of source segments prior to said comparison of said source material with said stored material.

14. A method according to claim 13, wherein said comparing comprises comparing said plurality of source segments with said stored material in said first natural language from a plurality of stored segments.

15. A method according to claim 13, wherein said identified part of source material comprises one or more of said plurality of source segments.

16. A method according to claim 13, wherein said source material is divided into said source segments where at least one of:

a full stop,

an exclamation mark,

a question mark,

a colon,

a semicolon,

a tab character, or

a paragraph mark,

appears in said source material.

17. A method according to claim 1, wherein said method comprises comparing said source material with preferred terminology material.

18. A method according to claim 17, wherein said replacement comprises replacing a part of said source material with a part of said preferred terminology material.

19. A method according to claim 1, wherein said method comprises comparing said source material with a set of options.

20. A method according to claim 19, wherein said replacement comprises replacing a part of said source material according to at least one option from said set of options.

21. A method according to claim 19, wherein said set of options comprises at least one of:

a spelling variant,

an abbreviation,

a contraction,

a compound word,

punctuation,

the length of a sentence,

a commonly misused word,

unnecessary wording, and

a combination of specific characters.

22. A method according to claim 19, wherein said options are user configurable.

23. A method according to claim 1, wherein said relationship comprises a correlation between said identified part of source material and said identified part of stored material.

24. A method according to claim 23, wherein said correlation comprises a correlation of at least a predetermined level.

25. A method according to claim 24, wherein said predetermined level is user configurable.

26. A method according to claim 23, wherein said correlation comprises a fuzzy logic match.

27. A method according to claim 1, wherein said outputting further comprises outputting data associated with said relationship.

28. A method according to claim 1, comprising said user inputting said source material into a first software process.

29. A method according to claim 28, wherein said outputting and replacing steps are carried out by said first software process.

30. A method according to claim 28, wherein said first software process comprises word processing software.

31. A method according to claim 28, wherein said comparing and identifying steps are carried out by a second software process.

32. A method according to claim 31, wherein said first software process interfaces with said second software process via an Application Program Interface (API).

33. A method according to claim 31, wherein said stored material is accessed by said second software process.

34. A method according to claim 1, further comprising removing said forbidden terminology material from said source material.

35. A method according to claim 1, wherein said forbidden terminology material comprises material unsuitable for inclusion by the user.

36. A method according to claim 35, wherein said forbidden terminology comprises at least one of:

terminology used by competitors;

terminology that may cause offense;

terminology that may cause confusion;

terminology that may damage a company'"'"'s reputation; and

terminology that may damage a company'"'"'s brand.

37. A method according to claim 1, further comprising providing a report associated with the source material indicating at least one of:

a number of parts of said source material which has a relationship in said first natural language with at least a part of said stored material;

a number of parts of said stored material identified;

a number of exact matches of said stored material identified;

a correlation of similarities between said source material and said stored material; and

a number of forbidden terms identified.

38. A method according to claim 37, wherein the report comprises at least one of a word processing document, a spreadsheet, a graph, a pie-chart, and an estimated translation cost savings.

39. A method according to claim 1, further comprising, after performing all of the method steps, performing a grammatical and stylistic check on the source material with said identified part of source material replaced with said identified part of said stored material.

40. A computer program product comprising a non-transitory computer-readable medium having computer readable instructions recorded thereon for natural language translation, the computer readable instructions being operative, when performed by a computerized device, to cause a computerized device to perform a method comprising:

a) comparing source material with stored material in a first natural language, said stored material having previously been translated from said first natural language to at least a second natural language;

b) identifying a part of said source material which has a relationship in said first natural language with at least a part of said stored material;

c) comparing said source material with forbidden terminology material;

d) outputting, in said first natural language, said identified part of source material and said identified part of stored material in a form suitable for review by a user; and

e) replacing said identified part of source material with said identified part of stored material in said first natural language to assist in subsequent full translation of said source material from said first natural language to at least said second natural language.

41. Apparatus for use in natural language translation, said apparatus including one or more computing platforms including memory and processing circuitry being collectively programmed to execute a plurality of components, the execution of the components causing the computing platforms to cooperatively perform a method comprising:

a) comparing source material with stored material in a first natural language, said stored material having previously been translated from said first natural language to at least a second natural language;

b) identifying at least a part of said source material which has a relationship in said first natural language with at least a part of said stored material;

c) comparing said source material with forbidden terminology material;

d) outputting, in said first natural language, said identified part of source material and said identified part of stored material in a form suitable for review by a user; and

e) replacing said identified part of source material with said identified part of stored material in said first natural language to assist in subsequent full translation of said source material from said first natural language to at least said second natural language.