File size: 2,464 Bytes
dc78b20 |
1 |
here .fi = f denotes tile (15ench) source and e{ = e denotes the (english) target string. most smt models (brown et al., 1993; vogel et al., 1996) try to model word-to-word corresl)ondences between source and target words using an alignment nmpl)ing from source l)osition j to target position i = aj. we can rewrite tim t)robal)ility pr(fille~) t) 3, in- troducing the hidden alignments ai 1 := al ...aj...a.l (aj c {0 , . , /} ) : pr(f~lel) = ~pr(f i ,a~le{) .1 ? j -1 i~ = e h pr(fj ajlf i -"al e l ) q, j=l to allow fbr french words wlfich do not directly cor- respond to any english word an artificial empty word c0 is added to the target sentence at position i=0. the different alignment models we present pro- vide different decoint)ositions of pr(f~,a~le(). an alignnlent 5~ for which holds a~ = argmax pr(fi , al[ei) at for a specific model is called v i terb i al ignment of" this model. in this paper we will describe extensions to tile hidden-markov alignment model froln (vogel et al., 1.996) and compare tlmse to models 1 - 4 of (brown et al., 1993). we t)roi)ose to measure the quality of an alignment nlodel using the quality of tlle viterbi alignment compared to a manually-produced align- ment. this has the advantage that once having pro- duced a reference alignlnent, the evaluation itself can be performed automatically. in addition, it results in a very precise and relia.ble valuation criterion which is well suited to assess various design decisions in modeling and training of statistical alignment mod- els. it, is well known that manually pertbrming a word aligmnent is a colnplicated and ambiguous task (melamed, 1998). therefore, to produce tlle refer- ence alignment we use a relined annotation scheme which reduces the complications and mnbiguities oc- curring in the immual construction of a word align- ment. as we use tile alignment models for machine translation purposes, we also evahlate the resulting translation quality of different nlodels. 2 al ignment w i th hmm in the hidden-markov alignment model we assume a first-order dependence for tim aligmnents aj and that the translation probability depends olfly on aj and not oil (tj_l: - ~- el) =p(ajl.a compar i son of a l ignment mode ls for s ta t i s t i ca l mach ine trans la t ion franz josef och and hermann ney lehrstuhl fiir informatik vi, comlmter science department rwth aachen - university of technology d-52056 aachen, germany {och, ney}~inf ormat ik. |