PERSONALIZED MACHINE TRANSLATION VIA ONLINE ADAPTATION

• US 20140149102A1
• Filed: 11/26/2012
• Published: 05/29/2014
• Est. Priority Date: 11/26/2012
• Status: Active Grant

• Current Assignee: SDL PLC (RWS Holdings Plc)
• Original Assignee: SDL PLC (RWS Holdings Plc)
• Inventors: Marcu, Daniel, May, Jonathan
• Granted Patent: US 9,152,622 B2
• Time in Patent Office: Days
• US Class Current: 704/2
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment
• CPC Class Codes: G06F 40/51 Translation evaluation

Abstract

Personalizing machine translation via online adaptation is described herein. According to some embodiments, methods for providing personalized machine translations may include receiving translator feedback regarding machine translations generated by a machine translation system for a translator, determining translator feedback that improves translations generated by the machine translation system, and incorporating the determined translator feedback into the translation methodology of the machine translation system to personalize the translation methodology.

Claims

1. A method for managing a personalized machine translation system, the method comprising:

receiving translator feedback regarding machine translations generated by a machine translation system for a translator, the machine translation system using a translation methodology;

determining translator feedback that improves translations generated by the machine translation system; and

incorporating the determined translator feedback into the translation methodology of the machine translation system to personalize the translation methodology.

2. The method according to claim 1, wherein the translation methodology comprises any of corpus-based machine translation, rule-based machine translation, transfer-based machine translation, hybrid-based machine translation, statistic-based machine translation, a translation memory, a language model, a translation dictionary, a phrase table, or any combination thereof.

3. The method according to claim 1, further comprising evaluating the translator feedback prior to the step of incorporating the translator feedback into the translation methodology to determine if the translator feedback comprises an improved translation relative to a translation generated by the machine translation system without the translator feedback.

4. The method according to claim 1, wherein translator feedback includes corrections that are received from the translator relative to a previous translation generated by the machine translation system.

5. The method according to claim 4, further comprising providing the corrections to a human translator and receiving verified corrections from the human translator, wherein the verified corrections are incorporated into translation methodology.

6. The method according to claim 1, further comprising evaluating translator feedback using a parallel corpus to validate the translator feedback.

7. The method according to claim 6, wherein the parallel corpus is selected by determining a domain associated with the translator and selecting a parallel corpus having a domain that is substantially similar to the domain of the translator.

8. The method according to claim 1, wherein the translator feedback comprises a triple having a source unit, a translation unit of the source unit, and a correction unit.

9. The method according to claim 8, further comprising providing an accuracy rating for any of the translation unit, the correction unit, or combinations thereof.

10. The method according to claim 8, wherein incorporating the translator feedback into the translation methodology comprises:

constructing a first translation table that comprises pairs of source units and correction units;

extracting dictionary entries from the translator feedback by;

preparing the pairs for alignment;

aligning words included in the pairs; and

extracting first phrase pairs based upon word alignment.

11. The method according to claim 10, wherein incorporating the translator feedback into the translation methodology comprises:

constructing a second translation table that comprises pairs of source units and translation units; and

extracting dictionary entries from the translator feedback by;

preparing the pairs for alignment;

aligning words included in the pairs; and

extracting second phrase pairs based upon word alignment.

12. The method according to claim 11, further comprising filtering the first and second phrase pairs by:

selecting first and second phrase pairs having a threshold amount of words included in the phrase;

selecting first and second phrase pairs that have terminal words which are aligned; and

including the selected first and second phrase pairs in the translation methodology of the machine translation system.

13. A personalized machine translation system, the system comprising:

a feedback processor that receives translator feedback regarding machine translations generated by a machine translation system for a translator, the machine translation system using a translation methodology;

a feedback classifier that determines translator feedback that improves translations generated by the machine translation system; and

a dictionary pusher that incorporates the translator feedback into the translation methodology of the machine translation system to personalize the translation methodology.

14. The system according to claim 13, wherein the translation methodology comprises any of corpus-based machine translation, rule-based machine translation, transfer-based machine translation, hybrid-based machine translation, statistic-based machine translation, a translation memory, a language model, a translation dictionary, a phrase table, or any combination thereof.

15. The system according to claim 13, wherein the feedback classifier further evaluates the translator feedback prior to the dictionary pusher incorporating the translator feedback into the translation methodology to determine if the translator feedback comprises an improved translation relative to a translation generated by the machine translation system without the translator feedback.

16. The system according to claim 13, wherein the feedback classifier further evaluates translator feedback using a parallel corpus to validate the translator feedback, wherein the parallel corpus is selected by determining a domain associated with the translator and selecting a parallel corpus having a domain that is substantially similar to the domain of the translator.

17. The system according to claim 13, wherein translator feedback includes corrections that are received from the translator relative to a previous translation generated by the machine translation system.

18. The system according to claim 17, wherein the feedback processor further provides the corrections to a human translator and receives verified corrections from the human translator, wherein the verified corrections are incorporated into translation methodology.

19. The system according to claim 13, wherein the translator feedback comprises a triple having a source unit, a translation unit of the source text, and a correction unit.

20. The system according to claim 19, wherein the feedback classifier further provides an accuracy rating for any of the translation unit, the correction unit, or combinations thereof.

21. The system according to claim 20, further comprising a dictionary extractor that:

constructs a first translation table that comprises pairs of source units and correction units; and

extracts dictionary entries from the translator feedback by;

preparing the pairs for alignment;

aligning words included in the pairs; and

extracting first phrase pairs based upon word alignment.

22. The system according to claim 21, wherein the dictionary extractor further:

constructs a second translation table that comprises pairs of source units and translation units; and

extracts dictionary entries from the translator feedback by;

preparing the pairs for alignment;

aligning words included in the pairs; and

extracting second phrase pairs based upon word alignment.

23. The system according to claim 22, wherein the dictionary extractor further filters the first and second phrase pairs by:

selecting first and second phrase pairs having a threshold amount of words included in the phrase;

selecting first and second phrase pairs that have terminal words which are aligned; and

storing the selected first and second phrase pairs in a translation phrase table that resides on a data repository.

24. A method for managing a personalized machine translation system, the method comprising:

receiving translator feedback regarding machine translations generated by a machine translation system for a translator, the machine translation system using a translation methodology;

determining translator feedback that improves translations generated by the machine translation system;

determining one or more translation preferences for the translator; and

incorporating the determined translator feedback and the translation preferences into the translation methodology of the machine translation system to personalize the translation methodology.

25. The method according to claim 24, wherein the one or more translation preferences comprises a domain for the translator.

26. The method according to claim 24, wherein the translation methodology further comprises feedback-based phrase pairs that include word alignments between source and correction sentence pairs.

27. The method according to claim 26, further comprising incorporating the feedback-based phrase pairs into a phrase pair database by analyzing features of the feedback-based phrase pairs, the features comprising properties that provide information indicative of a utility of the feedback-based phrase pairs.

28. The method according to claim 27, further comprising determining features of a feedback-based phrase pair by simulating phrase pair statistics using any of accumulated statistics for low-frequency words or established default values.

29. The method according to claim 24, further comprising generating a tuning corpus:

calculating a weighted value for each feature of a feedback-based phrase pair;

adding the weighted values together into an overall quality value; and

incorporating the feedback pair into the tuning corpus if the overall quality value meets or exceeds a threshold value.

30. The method according to claim 29, further comprising:

selecting new weights for features values to improve overall quality of future translations;

generating translations for translation requests; and

collecting new feedback-based translation pairs.

31. The method according to claim 24, further comprising determining if a feedback set is licensed, the feedback set comprising source text, a translation of the source text, and at least one correction for the translation, wherein a feedback set is licensed if the feedback set is included in an original machine translation of a sentence and in the at least one correction of the translation.

32. A method, comprising:

generating a personalized translation of a target sentence using a language model, the language model used to determine a likelihood that a target sentence is grammatically well-formed, independent of translation quality;

receiving a feedback-adjusted translation for the language model translation; and

incorporating the feedback-adjusted translation into a training corpus.

33. The method according to claim 32, wherein the language model is domain specific.

34. The method according to claim 32, further comprising modifying individual probabilities of the language model to correspond to differences between personalized translations and corresponding feedback-adjusted translations, wherein probabilities in of the language model are include a conditional likelihood of a target word of a target sentence relative to a fixed number of words preceding the target word.