|
|
|
|
Using Synchronous TAG for Source-Side Reordering in SMT
|
|
|
|
|
|
|
|
نویسنده
|
Mansouri Amin ,Fadaei Hakimeh ,Faili Heshaam ,Arabsorkhi Mohsen
|
|
منبع
|
international journal of information and communication technology research - 2013 - دوره : 5 - شماره : 4 - صفحه:47 -58
|
|
چکیده
|
Recent efforts in machine translation try to enrich statistical methods by syntactic information of sourceand target languages. in this paper we present a hybrid machine translator, which combines rule-based and statisticalmodels in a serial manner. this system uses synchronous tree adjoining grammar (stag) to benefit the contextsensitivity of this formalism. in this system, a set of reordering rules in stag formalism is automatically extractedfrom a parallel corpus. these rules are used to change the word orders of the source sentence to match the wordordersin the target language. the restructured sentences are then translated to target language using a statisticalapproach. experiments are carried out on three different datasets for english-persian translation. experimentalresults show that the presented reordering method combined with conventional or monotone phrase-based smt,improves the translation quality respectively by 1.8 and 0.55 points regarding bleu score.
|
|
کلیدواژه
|
Statistical Machine Translation ,Reordering Rules ,Tree Adjoining Grammar
|
|
آدرس
|
Engineering,College of Engineering, University of, School of Electrical and Computer Engineering,College of Engineering,, ایران, Engineering,College of Engineering, University of, School of Electrical and Computer Engineering,College of Engineering,, ایران, Engineering,College of Engineering, University of, School of Electrical and Computer Engineering,College of Engineering, ایران, Engineering,College of Engineering, University of, School of Electrical and Computer Engineering,College of Engineering,, ایران
|
|
پست الکترونیکی
|
marabsorkhi@ece.ut.ac.ir
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Authors
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|