Adaptive machine translation
View Patent ↗A computer-implemented method for providing information to an automatic machine translation system to improve translation accuracy is disclosed. The method includes receiving a collection of source text. An attempted translation that corresponds to the collection of source text is received from the automatic machine translation system. A correction input, which is configured to effectuate a correction of at least one error in the attempted translation, is also received. Finally, information is provided to the automatic machine translation system to reduce the likelihood that the error will be repeated in subsequent translations generated by the automatic machine translation system.
1. A computer-implemented method for providing information to an automatic machine translation system to improve translation accuracy, the method comprising:
receiving a collection of source text;
receiving from the automatic machine translation system an attempted translation that corresponds to the collection of source text;
receiving a correction input that is configured to effectuate a correction of at least one error in the attempted translation; and
providing information to be assimilated into a database of corresponding logical forms associated with the automatic machine translation system in order to reduce the likelihood that the error will be repeated in subsequent translations generated by the automatic machine translation system.
2. The method of claim 1 , wherein providing information comprises providing the correction input.
3. The method of claim 1 , further comprising transmitting update information across a network to be assimilated into a knowledge source associated with a different automatic machine translation system, the update information being configured to reduce the likelihood that the error will be repeated in subsequent translations generated by the automatic machine translation system.
4. The method of claim 1 , wherein receiving a correction input comprises receiving at least one correction instruction from a human translator.
5. A computer-implemented method for improving the performance of a user's specialized translation system that operates in association with an automatic machine translation system, comprising:
submitting a source text to the specialized translation system for assistance in translation;
identifying at least a portion of the source text for which the specialized translation system cannot provide a suitable translation;
receiving from the automatic machine translation system an attempted translation that corresponds to said at least a portion of the source text;
receiving a correction input from the user that is configured to effectuate a correction of at least one error in the attempted translation; and
providing information to be assimilated into a collection of parsing information associated with the automatic machine translation system so as to reduce the likelihood that the error will be repeated in subsequent translations generated by the automatic machine translation system.
6. The method of claim 5 , wherein providing information comprises providing the correction input.
7. The method of claim 5 , wherein the parsing information is configured to facilitate analysis of a collection of segments by a parser.
8. The method of claim 5 , further comprising transmitting update information across a network to be assimilated into a knowledge source associated with a different automatic machine translation system, the update information being configured to reduce the likelihood that the error will be repeated in subsequent translations generated by the automatic machine translation system.
9. The method of claim 5 , wherein receiving a correction input comprises receiving at least one correction instruction from a human translator.
10. The method of claim 5 , wherein identifying at least a portion of the source text for which the specialized translation system cannot provide a suitable translation comprises referencing confidence metric information.
11. The method of claim 5 , wherein identifying at least a portion of the source text for which the specialized translation system cannot provide a suitable translation comprises a manual translation evaluation.
12. A computer-implemented method for improving the performance of a user's specialized translation system that operates in association with an automatic machine translation system, comprising:
submitting a text to the specialized translation system for assistance in translation;
ascertaining that the specialized translation system cannot provide a suitable translation of the text;
receiving from the automatic machine translation system an attempted translation that corresponds to the text;
receiving a correction input from the user that is configured to effectuate a correction of at least one error in the text;
providing update information to be assimilated into a knowledge source associated with the automatic machine translation system, the update information being configured to reduce the likelihood that the error will be repeated in subsequent translations generated by the automatic machine translation system and
transmitting the update information across a network to be assimilated into a knowledge source associated with a different automatic machine translation system.
13. The method of claim 12 , wherein providing information comprises providing update information to be assimilated into a collection of groups of corresponding words or phrases associated with the automatic machine translation system.
14. The method of claim 12 , wherein receiving a correction input comprises receiving at least one correction instruction from a human translator.
15. The method of claim 12 , wherein ascertaining that the specialized translation system cannot provide a suitable translation of the text comprises referencing confidence metric information.
16. The method of claim 12 , wherein ascertaining that the specialized translation system cannot provide a suitable translation of the text comprises a manual translation evaluation.