CUNI Transformer Neural MT System for WMT18

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10390199" target="_blank" >RIV/00216208:11320/18:10390199 - isvavai.cz</a>

Result on the web

<a href="http://www.statmt.org/wmt18/pdf/WMT051.pdf" target="_blank" >http://www.statmt.org/wmt18/pdf/WMT051.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/W18-64051" target="_blank" >10.18653/v1/W18-64051</a>

Result language

angličtina

Original language name

CUNI Transformer Neural MT System for WMT18

Original language description

We describe our NMT system submitted to the WMT2018 shared task in news translation. Our system is based on the Transformer model (Vaswani et al., 2017). We use an improved technique of backtranslation, where we iterate the process of translating monolingual data in one direction and training an NMT model for the opposite direction using synthetic parallel data. We apply a simple but effective filtering of the synthetic data. We pre-process the input sentences using coreference resolution in order to disambiguate the gender of pro-dropped personal pronouns. Finally, we apply two simple post-processing substitutions on the translated output. Our system is significantly (p &lt; 0.05) better than all other English-Czech and Czech-English systems in WMT2018.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/DG16P02B048" target="_blank" >DG16P02B048: System for permanent preservation of documentation and presentation of historical sources from the period of totalitarian regimes</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the Third Conference on Machine Translation, Volume 2: Shared Tasks

ISBN

978-1-948087-81-0

ISSN

—

e-ISSN

neuvedeno

Number of pages

6

Pages from-to

486-491

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg, PA, USA

Event location

Bruxelles, Belgium

Event date

Oct 31, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—