System Description: The Submission of FOKUS to the WMT 19 Robustness Task

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427147" target="_blank" >RIV/00216208:11320/19:10427147 - isvavai.cz</a>

Result on the web

<a href="https://www.aclweb.org/anthology/W19-5363" target="_blank" >https://www.aclweb.org/anthology/W19-5363</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

System Description: The Submission of FOKUS to the WMT 19 Robustness Task

Original language description

This paper describes the systems of Fraunhofer FOKUS for the WMT 2019 machine translation robustness task. We have made submissions to the EN-FR, FR-EN, and JA-EN language pairs. The first two were made with a baseline translator, trained on clean data for the WMT 2019 biomedical translation task. These baselines improved over the baselines from the MTNT paper by 2 to 4 BLEU points, but where not trained on the same data. The last one used the same model class and training procedure, with induced typos in the training data to increase the model robustness.

Czech name

—

Czech description

—

Type

O - Miscellaneous

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

—

Publication year

2019

Confidentiality

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