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 : 149980
Doc. No : ET21772
Main Entry : Wen Wang
Title Proper : STATISTICAL PARSING AND LANGUAGE MODELING BASED ON CONSTRAINT DEPENDENCY GRAMMAR
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : This thesis focuses on the development of effective and efficient language rnodels(LMs) for speech recognition systems. We selected Constraint Dependency Grammar(CDG) as the underlying framework because CDG parses can be lexicalized a t theword level with a rich set of lexical features for modeling subcategorization and wh-movement without a combinatorial explosion of the parameter space and beca,useCDG is able to model languages with crossing dependencies and free word ordering.Two types of LMs were developed: an almost-parsing LM and a. full parser-based LM. The quality of these LMs gained significantly from the insights obtainedfrom initial CDG grammar induction experiments. The almost-parsing LM uses adata structure derived from CDG parses called a SuperARV that tightly integratesknowledge of words, lexical features, and syntactic constraints. The full CDG parser-based LM utilizes complete parse information obtained by adding the modifiee linksto the SuperARVs assigned to each word in a sentence in order to capture importantlong-distance dependency constraints...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 : TL44955.pdf
Title and statement of responsibility and : STATISTICAL PARSING AND LANGUAGE MODELING BASED ON CONSTRAINT DEPENDENCY GRAMMAR [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)