This link has been bookmarked by 4 people . It was first bookmarked on 07 Jan 2009, by Jody Foo.
-
27 Sep 11
-
Background
-
Marcu and Wong (EMNLP, 2002) proposed to establish phrase correspondences directly in a parallel corpus
-
phrase-based joint probability model
-
(i) a joint probability distribution φ(e, f), which reflects the probability that phrases e and f are translation equivalents; (ii) and a joint distribution d(i,j), which reflects the probability that a phrase at position i is translated into a phrase at position j
-
The decoder was originally developed for the phrase model proposed by Marcu and Wong
-
Maria no daba uma bofetada a la bruja verde
-
beam search algorithm
-
Among these the hypothesis with the lowest cost (highest probability) is selected as best translation
-
optimize the search by discarding hypotheses that cannot be part of the path to the best translation
-
define a beam of good hypotheses and prune out hypotheses that fall out of this beam
-
generate an (approximate) n-best list
-
our beam search does not only include the cost so far, but also an estimate of the future cost
-
-
04 Dec 09
-
07 Jan 09
-
We collect all aligned phrase pairs that are consistent with the word alignment
-
Would you like to comment?
Join Diigo for a free account, or sign in if you are already a member.