Machine translation apparatus and machine translation computer program

Abstract

A method of machine translation, using a bilingual corpus containing translation pairs each consisting of a sentence of a first language and a sentence of a second language, for translating an input sentence of the first language to the second language, including the steps of: receiving the input sentence of the first language and extracting, from the bilingual corpus, a sentence of the second language forming a pair with a sentence of the first language with highest similarity to the input sentence; applying an arbitrary modification among a plurality of predetermined modifications to the extracted sentence of the second language, and computing likelihood of sentences resulting from the modification; selecting a prescribed number of sentences having high likelihood from among the sentences resulting from the modification; repeating, on each of the sentences selected in the step of selecting, the steps of extracting, computing and selecting, until the likelihood no longer improves; and outputting, as a translation of the input sentence, a sentence having the highest likelihood among the sentences of the second language left at the end of the step of repeating.

Description

technical field [0001] The present invention relates to a machine translation device, especially a statistical machine translation device capable of performing high-precision translation while taking advantage of paradigmatic translation. Background technique [0002] In statistical translation, the problem of translating a sentence (J) in a certain language into a sentence (E) in another language is formalized as a problem of maximizing the probability of the following condition. [0003] E ^ = arg max E P ( E | J ) [0004] For this formula, the following formula is obtained by applying Bayes' theorem. [0005] E ^ = arg max E P ( ...

AI Technical Summary

Problems solved by technology

However, in the usual search algorithm, if the search is performed in a limited space in this way, search errors will inevitably occur

We admit that there is some degree of correlation between the quality of the translation and the similarity assigned by the translation model, but it is difficult to obtain higher quality by beam search

[0024] In addition, in the method of German et al., there are many problems in obtaining local most appropriate solutions in the search, and it is impossible to obtain high-precision solutions stably.

Images