Dynamic generation of auto-suggest dictionary for natural language translation

• US 8,935,150 B2
• Filed: 09/05/2013
• Issued: 01/13/2015
• Est. Priority Date: 03/02/2009
• Status: Active Grant

• Current Assignee: SDL Ltd.
• Original Assignee: SDL PLC (RWS Holdings Plc)
• Inventors: Christ, Oliver
• Primary Examiner(s): Neway, Samuel G
• Application Number:
  US14/019,480
• Publication Number:
  US 20140006006A1
• Time in Patent Office: 495 Days
• Field of Search: 704 1- 10
• US Class Current: 704/2
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• 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 40/49 using very large corpora, e.g. the web
• 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

The present technology dynamically generates auto-suggest dictionary data from translation data stored in memory at a server. The auto-suggest dictionary data may be transmitted to a remote device by the server for use in language translation. The auto-suggest dictionary data may be transferred as part of a package which includes content to be translated, translation meta-data, and various other data. The auto-suggest dictionary data may be generated at a first computing device, periodically or in response to an event, from translation data stored in memory. The auto-suggest dictionary may be transferred to a remote device along with content to be translated and other data, as part of a package, for use in translation of the content at the remote device.

Claims

1. A method for suggesting translation text comprising:

receiving content for translation from a source language to a target language, and metadata describing a translation job;

extracting an auto-suggest dictionary from translation units including sentence pairs comprising a sentence in a source language and a translation of the sentence in the target language;

generating a translation package including the extracted auto-suggest dictionary and the received content and the metadata;

sending the translation package to a remote device configured for assisting a user in translating the received content, the assisting including;

displaying to a user a graphical user interface (GUI) containing the received content;

receiving from the user one or more first characters of a translation of the displayed content;

predicting a plurality of subsequent characters of the translation of the displayed content based on the auto-suggest dictionary and the metadata;

displaying to the user the received one or more first characters and the plurality of subsequent characters of the translation; and

receiving from the user a selection from the plurality of subsequent characters;

receiving translation units of the source language content from the remote device, the translation units of the source language content based on the selection from the plurality of subsequent characters; and

updating the auto-suggest dictionary from the received translation units of the source language content.

2. The method of claim 1, further comprising monitoring keystrokes of a translator providing the one or more first characters.

3. The method of claim 2, further comprising comparing the keystrokes to a glossary list.

4. The method of claim 1, further comprising scanning a translation memory and original source text for matches.

5. The method of claim 4, further comprising autocompleting the translation based on matches from the scanned translation memory and received first characters.

6. The method of claim 1, the predicting further comprising referencing a database.

7. The method of claim 6, wherein the database comprises a bilingual corpus.

8. The method of claim 1, further comprising:

receiving second characters of the translation of the displayed source language;

predicting revised subsequent characters of the translation of the displayed source language in view of the received first and second characters of the translation of the displayed source language; and

displaying the received first characters, the received second characters, and the revised subsequent characters of the translation.

9. The method of claim 8, wherein the received second characters comprises deletion of at least one of the received first characters of the translation of the displayed source language.

10. A translation text suggesting system comprising:

a server configured to;

receive content for translation from a source language to a target language, and metadata describing a translation job;

extract an auto suggest dictionary from translation units including sentence pairs comprising a sentence in a source language and a translation of the sentence in the target language;

generate a translation package including the extracted auto suggest dictionary, the content and the metadata;

send the translation package to a remote device configured for assisting a user in translating the content; and

extract an updated auto suggestion dictionary based on translation unit content received from the remote device, the translation unit content based on the content;

a processor disposed on the remote device, the processor configured to execute instructions stored in memory; and

a memory, coupled to the processor, the memory comprising instructions executable by the processor to;

display to the user a graphical user interface (GUI) containing the content received from the server;

receive first characters of a translation of the displayed content from the user;

predict subsequent characters of the translation of the displayed content based on the auto suggest dictionary and the metadata;

display the received first characters and predicted subsequent characters of the translation to the user;

select subsequent characters from the predicted subsequent characters; and

send the translation unit content to the server, the translation unit content based on the selected subsequent characters.

11. The system of claim 10, the memory further comprising instructions executable by the processor to monitor keystrokes of a translator providing the first characters.

12. The system of claim 11, the memory further comprising instructions executable by the processor to compare the keystrokes to a glossary list.

13. The system of claim 10, the memory further comprising instructions executable by the processor to scan a translation memory and original source text for matches.

14. The system of claim 13, the memory further comprising instructions executable by the processor to autocomplete the translation based on matches from the scanned translation memory and the received first characters.

15. The system of claim 10, wherein the instruction for predicting further comprises referencing a database.

16. The system of claim 15, wherein the database comprises a bilingual corpus.

17. The system of claim 10, the memory further comprising instructions executable by the processor to:

receive second characters of the translation of the displayed source language;

predict revised subsequent characters of the translation of the displayed source language in view of the received first and second characters of the translation of the displayed source language; and

display the received first characters, the received second characters, and the revised subsequent characters of the translation.

18. The system of claim 17 wherein the received second characters comprises deletion of at least one of the received first characters of the translation of the displayed source language.

19. A non-transitory computer readable storage medium having embodied thereon a program, the program being executable by a processor to perform a method for suggesting translation text, the method comprising:

receiving a translation package from a server, the translation package including an auto-suggest dictionary, content for translation from a source language to a target language, and metadata describing a translation job, the auto-suggest dictionary extracted from translation units of a translation memory, each translation unit including a sentence pair comprising a sentence in a source language and an aligned translation of the sentence in the target language;

displaying to a user a graphical user interface (GUI) containing the received content;

receiving first characters of a translation of the displayed content from the user;

predicting a plurality of translations of the displayed content based on the received auto-suggest dictionary and the metadata;

displaying the plurality of predicted translations;

receiving from the user a selection of a translation from the plurality of predicted translations;

sending to the server a translation unit of the source language content including the selected translation; and

adding the translation unit of the source language content to the translation memory.

20. The non-transitory computer readable storage medium of claim 19, further comprising:

receiving second characters of the translation of the displayed source language;

predicting revised subsequent characters of the translation of the displayed source language in view of the received first and second characters of the translation of the displayed source language; and

displaying the received first characters, the received second characters, and the revised subsequent characters of the translation.