eprintid: 3381
rev_number: 9
eprint_status: archive
userid: 345
dir: disk0/00/00/33/81
datestamp: 2018-12-25 11:04:50
lastmod: 2018-12-25 11:04:50
status_changed: 2018-12-25 11:04:50
type: conference_item
metadata_visibility: show
creators_name: Tran Hong, Viet
creators_name: Nguyen Hoang, Quan
creators_name: Nguyen Van, Vinh
creators_id: thviet@uneti.edu.vn
creators_id: quan94fm@gmail.com
creators_id: vinhnv@vnu.edu.vn
corp_creators: 1University of Economic and Technical Industries,Hanoi, Vietnam
corp_creators: VNU University of Engineering and Technology
corp_creators: VNU University of Engineering and Technology
title: A Neural Network Classifier Based on Dependency Tree for English-Vietnamese Statistical Machine Translation
ispublished: inpress
subjects: IT
divisions: fac_fit
abstract: Reordering in MT is a major challenge when translating between languages with different of sentence structures. In Phrase-based statistical machine translation (PBSMT) systems, syntactic pre-ordering is a commonly used preprocessing technique. This technique can be used to adjust the syntax of the source language to that of the target language by changing the word order of a source sentence prior to translation and solving to overcome a weakness of classical phrase-based translation systems: long distance reordering. In this paper, we propose a new pre-ordering approach by defining dependency-based features and using a neural network classifier for reordering the words in the source sentence into the same order in target sentence. Experiments on English-Vietnamese machine translation showed that our approach yielded a statistically significant improvement compared to our prior baseline phrase-based SMT system.
date: 2018
full_text_status: public
pres_type: paper
event_title: Cicling 2018
event_type: conference
refereed: FALSE
citation:   Tran Hong, Viet and Nguyen Hoang, Quan and Nguyen Van, Vinh  (2018) A Neural Network Classifier Based on Dependency Tree for English-Vietnamese Statistical Machine Translation.  In: Cicling 2018.    (In Press)  
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3381/1/CICLing2018_paper19.pdf