Machine translation apparatus and machine translation computer program

A recording medium recording a machine translation computer program causing, when executed by a computer, the computer to perform a method of machine translation using a bilingual corpus containing a plurality of translation pairs each consisting of a sentence of a first language and a sentence of a second language, for translating an input sentence of said first language to said second language, said method including steps of:

• receiving the input sentence of said first language;
• computing a score between the input sentence and a plurality of sentences of the first language contained in said bilingual corpus;
• identifying, based on the result of said step of computing the score, a first sentence among the plurality of sentences of the first language having a prescribed score representing a similarity to the input sentence;
• extracting, from said bilingual corpus, a sentence of said second language forming a pair with the first sentence;
• applying an arbitrary modification among a plurality of predetermined modifications to said extracted sentence of said second language, and computing likelihood of sentences resulting from the modification;
• selecting sentences having the likelihood satisfying a prescribed condition from among the sentences resulting from the modification;
• repeating, on each of the sentences selected in said step of selecting, said steps of extracting, computing the likelihood and selecting, until a predetermined termination condition is satisfied;
• and
• outputting, as a translation of said input sentence, a sentence having the likelihood satisfying a predetermined selection condition among the sentences of said second language left at the end of said step of repeating, wherein:
• said step of computing the score includes computing a score between the input sentence and each sentence of said first language contained in said bilingual corpus, the step of computing the score includes steps of computing a prescribed measure of similarity, using document frequency defined on said input sentence regarding a sentence of said first language contained in said bilingual corpus as a document, between said input sentence and each of the sentences of said first language contained in said bilingual corpus, computing edit distance between said input sentence and each of the sentences of said first language contained in said bilingual corpus, and computing said score based on the measure of similarity computed in said step of computing similarity and on the edit distance computed in said step of computing edit distance,
• said step of identifying the first sentence includes identifying a first sentence of said first language having the highest score, computed in said step of computing the score,
• said step of extracting the sentence of said second language includes extracting, from said bilingual corpus, a sentence of said second language forming a pair with the first sentence having the highest score, computed in said step of computing the score, and
• said step of computing similarity includes the step of computing a tf/idf criteria Ptf/idf in accordance with the following equation, between each sentence of said first language contained in said bilingual corpus and said input sentence:
• P
• tf
• /
• idf
• ⁡
• (
• J
• k
• ,
• J
• 0
• )
• =
• ∑
• i
• :
• J
• 0
• ,
• i
• ∈
• J
• k
• ⁢
• ⁢
• log
• ⁡
• (
• N
• /
• df
• ⁡
• (
• J
• 0
• ,
• i
• )
• )
• /
• log
• ⁢
• ⁢
• N
• 
• J
• 0
• 
• where Jo is the input sentence, Jo,i is the i-th word of input sentence Jo, df(Jo,i) is the document frequency for the word Jo,i, Jk is a k-th sentence of said first language (1≦k ≦N) and N is the total number of translation pairs in the bilingual corpus.