E-services translation utilizing machine translation and translation memory

• US 10,216,731 B2
• Filed: 01/19/2017
• Issued: 02/26/2019
• 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:
  US15/410,471
• Publication Number:
  US 20170132214A1
• Time in Patent Office: 768 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:

calling an application programming interface and utility based on a file format of a document to extract translatable strings from the document;

machine translating an inputted source to produce a target string, the inputted source comprising one of the extracted translatable strings;

comparing human generated target strings and the machine translated target string;

locating a match between a human generated target string of the human generated target strings and the machine translated target string using a translation database, the translation database comprising a collection of source language sentences and target language sentences, where none of the source language sentences and target language sentences are paired together;

when the match is not found, sending the machine translated target string for subsequent review by a human translator; and

when the match is found, outputting the matching human generated target string for subsequent review by the human translator.

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

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

4. A machine for translating data from a source language to a target language, comprising:

a processor; and

a memory for storing executable instructions, the processor executing the instructions to;

call an application programming interface and utility based on a file format of a document;

extract translatable strings from the document using the utility;

machine translate an inputted source to produce a target string, the inputted source comprising one of the extracted translatable strings;

compare human generated target strings and the machine translated target string;

locate a match between a human generated target string of the human generated target strings and the machine translated target string using a translation database, the translation database comprising a collection of source language sentences and target language sentences, where none of the source language sentences and target language sentences are paired together;

when the match is not found, transmit the machine translated target string for subsequent review by a human translator; and

when the match is found, output the matching human generated target string for subsequent review by the human translator.

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

6. The machine of claim 4 wherein the translation database comprises strings of source data and non-matching strings of target data.