A Proposed Model for Enhancing Lexical Statistical Machine Translation (ELSMT)

نوع المستند : • البحوث والدراسات والمقالات المستوفاة للقواعد العلمیة المتعارف علیها، والتى یجریها أو یشارک فى إجرائها أعضاء هیئة التدریس والباحثون فى الجامعات ومراکز البحوث المصریة والعربیة، وذلک باللغتین العربیة والإنجلیزیة .

المؤلفون

Sadat Academy for Management Sciences

المستخلص

ABSTRACT
Statistical Machine Translation (SMT) deals with automatically mapping sentences in one human language into another  human language. This means that it translates from the source language to the target language, so the goal of SMT is automatically analyze existing human sentence translations, to build general translation model for translation.
A model presented for efficiently incorporate models, which used before in statistical machine translation such as language model, alignment model, phrase based model, reordering model, and translation model. These models combined to enhance the performance of statistical machine translation (SMT). One of the advantages of the statistical approach to machine  translation is that it is largely language agnostic. Machine translation models used to learn automatically translation patterns from data. This research introduces a model, which might be used to translate from the source to the target sentence automatically.
There are many tools have been used in this work such as Gizaa++. All these tools used to take the advantage of the previous mentioned models combined together with each other.
Finally, based on the implementation of this model, it has proved that this model has improved the result of the statistical machine translation.

الكلمات الرئيسية

الموضوعات الرئيسية

ملفات

شارك

إرسال الاستشهاد إلى

الإحصائيات