eprintid: 3870
rev_number: 8
eprint_status: archive
userid: 345
dir: disk0/00/00/38/70
datestamp: 2019-12-19 16:05:08
lastmod: 2019-12-20 04:47:54
status_changed: 2019-12-19 16:05:08
type: conference_item
metadata_visibility: show
creators_name: Pham, Nghia Luan
creators_name: Nguyen, Van Vinh
creators_id: luanpn@dhhp.edu.vn
creators_id: vinhnv@vnu.edu.vn
title: Adapting Neural Machine Translation for English-Vietnamese using Google Translate system for Back-translation
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: In this paper, we propose a method to better
leveraging monolingual data by exploiting the
advantages of GNMT system. Our method
for adapting a general neural machine translation
system to a specific domain, by exploiting
Back-translation technique using targetside
monolingual data. This solution requires
no changes to the model architecture from a
standard NMT system. Experiment results
show that our method can improve translation
quality, results significantly outperforming
strong baseline systems, our method improves
translation quality in legal domain up
to 13.65 BLEU points over the baseline system
for English-Vietnamese pair language.
date: 2019
date_type: published
full_text_status: public
pres_type: paper
event_title: Paclic 2019
event_type: conference
refereed: TRUE
citation:   Pham, Nghia Luan and Nguyen, Van Vinh  (2019) Adapting Neural Machine Translation for English-Vietnamese using Google Translate system for Back-translation.  In: Paclic 2019.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3870/1/PACLIC%202019%20-%20Camera_ready.pdf