Please use this identifier to cite or link to this item: http://artemis.cslab.ece.ntua.gr:8080/jspui/handle/123456789/16866
Full metadata record
DC FieldValueLanguage
dc.contributor.authorΑναστασόπουλος Αντώνιος
dc.date.accessioned2018-07-23T19:17:05Z-
dc.date.available2018-07-23T19:17:05Z-
dc.date.issued2014-4-22
dc.date.submitted2014-4-9
dc.identifier.urihttp://artemis-new.cslab.ece.ntua.gr:8080/jspui/handle/123456789/16866-
dc.description.abstractThe automatic estimation of Machine Translation output quality is a hard task, where the selection of the appropriate algorithm and the most predictive features often plays a crucial role. When moving from controlled lab evaluations to real-life scenarios the task becomes even harder. For current Machine Translation Quality Estimation systems, additional complexity comes from the difficulty to model user and domain changes. Systems' instability with respect to data coming from different distributions, in fact, calls for adaptive solutions that quickly react to new operating conditions. To tackle this issue we propose an online framework for adaptive Quality Estimation, targeting reactivity and robustness to user and domain changes.We experiment with different online machine learning techniques like Online Support Vector Regression, Passive Aggressive Algorithms and Online Gaussian Processes. We also perform contrastive experiments with two language pairs, English-Spanish and English-Italian, in different testing conditions. The outcome of the experiments demonstrates the effectiveness of this approach.
dc.languageEnglish
dc.subjectquality estimation
dc.subjectmachine translation
dc.subjectadaptive learning
dc.titleOnline Learning For Automatic Quality Estimation Of Machine Translation Output
dc.typeDiploma Thesis
dc.description.pages117
dc.contributor.supervisorΜαΐστρος Γιάννης
dc.departmentΤομέας Τεχνολογίας Πληροφορικής & Υπολογιστών
dc.organizationΕΜΠ, Τμήμα Ηλεκτρολόγων Μηχανικών & Μηχανικών Υπολογιστών
Appears in Collections:Διπλωματικές Εργασίες - Theses

Files in This Item:
File SizeFormat 
DT2014-0102.pdf1.69 MBAdobe PDFView/Open


Items in Artemis are protected by copyright, with all rights reserved, unless otherwise indicated.