E-services translation utilizing machine translation and translation memory

• US 9,600,472 B2
• Filed: 03/18/2011
• Issued: 03/21/2017
• Est. Priority Date: 09/17/1999
• Status: Expired due to Fees

• Current Assignee: SDL PLC (RWS Holdings Plc)
• Original Assignee: SDL PLC (RWS Holdings Plc)
• Inventors: Cheng, Shang-Che, Pressman, Alexander, Zhang, Hong, Ma, Pei Chiang, Zhang, Shuan, Hummel, Jochen
• Primary Examiner(s): He, Jialong
• Application Number:
  US13/052,041
• Publication Number:
  US 20120046934A1
• Time in Patent Office: 2,195 Days
• Field of Search: 704 1- 8
• US Class Current: 1/1
• 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 40/51 Translation evaluation
• 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 system and method for translating data from a source language to a target language is provided wherein machine generated target translation of a source sentence is compared to a database of human generated target sentences. If a matching human generated target sentence is found, the human generated target sentence may be used instead of the machine generated sentence, since the human generated target sentence is more likely to be a well-formed sentence than the machine generated sentence. The system and method does not rely on a translation memory containing pairs of sentences in both source and target languages, and minimizes the reliance on a human translator to correct a translation generated by machine translation.

Claims

1. A method for translating data from a source language to a target language, comprising:

inputting source data for translation;

first searching a database for a source string similar to the inputted source data, said source string having a corresponding translated target string;

outputting said corresponding translated target string if said source string similar to said inputted source data is found;

reviewing, via a human translator, said corresponding translated target string;

machine translating said inputted source data if said source string similar to said inputted source data is not found, said machine translating producing a target string;

second searching said database for a matching target string that matches the target string produced by said machine translating, the second searching being performed by comparing the target string and the matching target string; and

outputting the matching target string if said matching target string is found.

2. The method of claim 1, further comprising

sending said machine translated target string for subsequent review by said human translator if the matching target string is not found in said database.

3. The method of claim 1, wherein the database comprises strings of source data and matching strings of target data.

4. The method of claim 1, wherein the machine translating comprises using units of data smaller than a sentence.

5. The method of claim 1, wherein the machine translating comprises using a bilingual corpus to align phrases and words between the source language and the target language.

6. The method of claim 1, wherein the database comprises strings of source data and non-matching strings of target data.

7. The method of claim 1, wherein the database comprises a collection of source language sentences and target language sentences, where none of the source language sentences and target language sentences are paired together.

8. A method for translating data from a source language to a target language, comprising:

inputting source data for translation;

first searching a database for a source string similar to the inputted source data, said source string having a corresponding translated target string;

outputting said corresponding translated target string if said source string similar to said inputted source data is found;

reviewing, via a human translator, said corresponding translated target string;

machine translating said inputted source data if said source string similar to said inputted source data is not found, said machine translating producing a target string;

second searching the database for a matching target string similar to the target string, the second searching being performed by comparing the target string and the matching target string; and

reviewing the matching target string by said human translator if said matching target string is found.

9. A method for translating from a source language to a target language, comprising:

receiving a source string in the source language;

first searching a translation database for a similar source string in the source language, the similar source string being similar to the source string;

machine translating the source string from the source language into the target language to produce a machine translated target string if the similar source string is not found in the search of said translation database;

second searching said translation database for a similar target string in the target language, the similar target string being similar to the machine translated target string and the second searching being performed by comparing the similar target string and the machine translated target string; and

outputting the similar target string as a translation of the source string when the similar target string is found in the translation database.

10. The method of claim 9, wherein the similar source string has a corresponding translated target string.

11. The method of claim 10, further comprising outputting the corresponding translated target string as the translation of the source string when the similar source string is found.

12. The method of claim 9, further comprising outputting the machine translated target string when the similar target string is not found in the database, the machine translated target string being output for subsequent review by a human translator to form the translation of the source string.