My Library

University LibraryCatalogue

Limit search to items available for borrowing or consultation
Result Page: Previous Next
Can't find that book? Try BONUS+
Look for full text

Search Discovery

Search CARM Centre Catalogue

Search Trove

Add record to RefWorks

Cover Art
Author Tambouratzis, George.

Title Machine translation with minimal reliance on parallel resources / George Tambouratzis, Marina Vassiliou, Sokratis Sofianopoulos.

Published Cham : Springer, 2017.


Location Call No. Status
Physical description 1 online resource.
Series SpringerBriefs in statistics, 2191-544X
SpringerBriefs in statistics.
Springer Mathematics and Statistics eBooks 2017 English+International
Bibliography Includes bibliographical references.
Contents Preliminaries -- Implementation -- Main translation process -- Assessing PRESEMT -- Expanding the system -- Extensions to the PRESEMT methodology -- Conclusions and future work -- References.
Summary This book provides a unified view on a new methodology for Machine Translation (MT). This methodology extracts information from widely available resources (extensive monolingual corpora) while only assuming the existence of a very limited parallel corpus, thus having a unique starting point to Statistical Machine Translation (SMT). In this book, a detailed presentation of the methodology principles and system architecture is followed by a series of experiments, where the proposed system is compared to other MT systems using a set of established metrics including BLEU, NIST, Meteor and TER. Additionally, a free-to-use code is available, that allows the creation of new MT systems. The volume is addressed to both language professionals and researchers. Prerequisites for the readers are very limited and include a basic understanding of the machine translation as well as of the basic tools of natural language processing.
Other author Vassiliou, Marina.
Sofianopoulos, Sokratis.
SpringerLink issuing body.
Subject Machine translating.
Electronic books.
ISBN 9783319631073 (electronic bk.)
3319631071 (electronic bk.)
Standard Number 10.1007/978-3-319-63107-3