خط مشی دسترسیدرباره ما
ثبت نامثبت نام
راهنماراهنما
فارسی
ورودورود
صفحه اصلیصفحه اصلی
جستجوی مدارک
تمام متن
منابع دیجیتالی
رکورد قبلیرکورد بعدی
Document Type : Latin Dissertation
Language of Document : English
Record Number : 149960
Doc. No : ET21752
Main Entry : Baltimore, Maryland
Title Proper : Bitext Alignment for St at istical Machine Translation
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : Bitext alignment is the task of finding translation equivalence between documentsin two languages, collections of which are commonly known as bitext. This disser-tation addresses the problems of statistical alignment at various granularities fromsentence to word with the goal of creating Statistical Machine Translation (SMT)systems.SMT systems are statistical pattern processors based on parameterized modelsestimated from aligned bitext training collections. The collections are large enoughthat alignments must be created using automatic methods. The bitext collectionsare often available as aligned documents, such as news stories, which usually need tobe further aligned at the sentence level and the word level before statistics can beextracted from the bitext. We develop statistical models that are learned from datain an unsupervised way. Language..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject : Electericl tess
: برق
electronic file name : TL44934.pdf
Title and statement of responsibility and : Bitext Alignment for St at istical Machine Translation [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)