Machine translation techniques
First Claim
1. A machine translation decoding method comprising:
- receiving as input a text segment in a source language to be translated into a target language;
generating an initial translation as an initial current target language translation;
estimating a probability of correctness of the initial translation, the probability based on alignment links between words and phrases in the source language and words and phrases in the target language;
applying one or more modification operators to the initial current target language translation by a computer to generate one or more modified target language translations;
estimating a probability of correctness of the one or more modified target language translations, the probability based on alignment links between words and phrases in the source language and words and phrases in the target language;
determining by the computer whether one or more of the modified target language translations represents an improved translation in comparison with the initial current target language translation by comparing the estimated probability of correctness of the initial translation with the estimated probability of correctness of the one or more modified target language translations;
setting by the computer a modified target language translation with a higher probability based on the comparison as the modified current target language translation; and
repeating said applying, said determining and said setting for the modified current target language translation until occurrence of a termination condition andoutputting the modified current target language translation by the computer in response to the occurrence of the termination condition.
1 Assignment
0 Petitions
Accused Products
Abstract
Machine translation decoding is accomplished by receiving as input a text segment in a source language to be translated into a target language, generating an initial translation as a current target language translation, applying one or more modification operators to the current target language translation to generate one or more modified target language translations, determining whether one or more of the modified target language translations represents an improved translation in comparison with the current target language translation, setting a modified target language translation as the current target language translation, and repeating these steps until occurrence of a termination condition. Automatically generating a tree (e.g., either a syntactic tree or a discourse tree) can be accomplished by receiving as input a tree corresponding to a source language text segment, and applying one or more decision rules to the received input to generate a tree corresponding to a target language text segment.
-
Citations
33 Claims
-
1. A machine translation decoding method comprising:
-
receiving as input a text segment in a source language to be translated into a target language; generating an initial translation as an initial current target language translation; estimating a probability of correctness of the initial translation, the probability based on alignment links between words and phrases in the source language and words and phrases in the target language; applying one or more modification operators to the initial current target language translation by a computer to generate one or more modified target language translations; estimating a probability of correctness of the one or more modified target language translations, the probability based on alignment links between words and phrases in the source language and words and phrases in the target language; determining by the computer whether one or more of the modified target language translations represents an improved translation in comparison with the initial current target language translation by comparing the estimated probability of correctness of the initial translation with the estimated probability of correctness of the one or more modified target language translations; setting by the computer a modified target language translation with a higher probability based on the comparison as the modified current target language translation; and repeating said applying, said determining and said setting for the modified current target language translation until occurrence of a termination condition and outputting the modified current target language translation by the computer in response to the occurrence of the termination condition. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A computer-implemented machine translation decoding method comprising:
-
receiving as input a text segment in a source language to be translated into a target language; generating an initial translation by the computer as an initial current target language translation; estimating a probability of correctness of the initial translation by the computer, the probability based on alignment links between words and phrases in the source language and words and phrases in the target language; applying one or more modification operators by the computer to the initial current target language translation to generate one or more modified target language translations; estimating a probability of correctness of the one or more modified target language translations, the probability based on alignment links between words and phrases in the source language and words and phrases in the target language; determining by the computer whether one or more of the modified target language translations represents an improved translation in comparison with the initial current target language translation by comparing the estimated probability of correctness of the initial translation with the estimated probability of correctness of the one or more modified target language translations; iteratively modifying the current target language translation of the source language text segment based on the determination; and repeating said applying, said determining and said iteratively modifying until occurrence of a termination condition. - View Dependent Claims (16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26)
-
-
27. A machine translation decoder comprising:
-
a memory, the memory containing program instructions configured to be executed by a processor; a processor able to access and execute the program instructed stored in the memory; a decoding engine, configured to receive as input a text segment in a source language to be translated into a target language and to generate an initial translation as a current target language translation, comprising one or more modification operators to be applied to a current target language translation to generate one or more modified target language translations; a probability module in communication with the decoding engine configured to estimate a probability of correctness of the initial translation, the probability based on alignment links between words and phrases in the source language and words and phrases in the target language, to estimate a probability of correctness of the one or more modified target language translations, the probability based on alignment links between words and phrases in the source language and words and phrases in the target language, and to determine whether one or more of the modified target language translations represents an improved translation in comparison with the initial current target language translation by comparing the estimated probability of correctness of the initial translation with the estimated probability of correctness of the one or more modified target language translations; and a process loop configured to iteratively modify the current target language translation of a source language text based on the probability module estimate of the probability of correctness of the one or more modified target language translations and the probability module determination regarding whether one or more of the modified target language translations represent an improved translation, the process loop terminating upon occurrence of a termination condition. - View Dependent Claims (28, 29, 30, 31, 32, 33)
-
Specification