E-services translation utilizing machine translation and translation memory

• US 10,198,438 B2
• Filed: 06/20/2014
• Issued: 02/05/2019
• Est. Priority Date: 09/17/1999
• Status: Expired due to Fees

• Current Assignee: Tradis Incorporated
• 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:
  US14/311,213
• Publication Number:
  US 20150142415A1
• Time in Patent Office: 1,691 Days
• 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;

searching a database for a source string similar to the inputted source data, said source string having a 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;

searching said database for a human generated target string matching the target string produced by said machine translating, the searching being performed by comparing the target string produced by said machine translating and the matching human generated target string, wherein said database comprises at least one human generated target string that is not paired with a corresponding source string; and

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

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.

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

searching a database for a source string similar to inputted source data;

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

searching said database for a matching human generated target string that matches the target string produced by said machine translating, the searching being performed by comparing the target string produced by said machine translating and the matching human generated target string, wherein said database comprises at least one human generated target string that is not paired with a corresponding source string; and

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