Paraphrasing and Translation - part 3

Xác suất một từ nước ngoài FJ là bản dịch của một ei từ tiếng Anh. Xác suất mà một ei từ sẽ mở rộng vào các từ φi trong ngôn ngữ nước ngoài. Xác suất mà một từ giả mạo sẽ được chèn vào bất kỳ điểm nào trong một câu. | . The use of parallel corpora for statistical machine translation 23 translation probabilities t fj lei The probability that a foreign word fj is the translation of an English word ei. fertility probabilities n ội ei The probability that a word ei will expand into ội words in the foreign language. spurious word probability p The probability that a spurious word will be inserted at any point in a sentence. distortion probabilities d Pili l m The probability that a target position pi will be chosen for a word given the index of the English word that this was translated from i and the lengths l and m of the English and foreign sentences. Table The IBM Models define translation model probabilities in terms of a number of parameters including translation fertility distortion and spurious word probabilities. problem of determining whether a sentence is a good translation of another into the problem of determining whether there is a sensible mapping between the words in the sentences like in the alignments in Figure . Brown et al. defined a series of increasingly complex translation models referred to as the IBM Models which define p f a e . IBM Model 3 defines word-level alignments in terms of four parameters. These parameters include a word-for-word translation probability and three less intuitive probabilities fertility spurious word and distortion which account for English words that are aligned to multiple foreign words words with no counterparts in the foreign language and word re-ordering across languages. These parameters are explained in Table . The probability of an alignment p f a e is calculated under IBM Model 3 as 1 l m m p f a e n n e nt fj Iei nd jiaj 1 m If a bilingual parallel corpus contained explicit word-level alignments between its sentence pairs like in Figure then it would be possible to directly estimate the parameters of the IBM Models using maximum likelihood estimation. However since word-aligned parallel corpora do not .