CUNI System for the WMT19 Robustness Task

Jindřich Helcl, Jindřich Libovický, Martin Popel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present our submission to the WMT19 Robustness Task. Our baseline system is the Charles University (CUNI) Transformer system trained for the WMT18 shared task on News Translation. Quantitative results show that the CUNI Transformer system is already far more robust to noisy input than the LSTM-based baseline provided by the task organizers. We further improved the performance of our model by fine-tuning on the in-domain noisy data without influencing the translation quality on the news domain.
Original languageEnglish
Title of host publicationProceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
Place of PublicationFlorence, Italy
PublisherAssociation for Computational Linguistics
Pages539-543
Number of pages5
ISBN (Electronic)978-1-950737-27-7
DOIs
Publication statusPublished - 1 Aug 2019
EventACL 2019 Fourth Conference on Machine Translation - Florence, Italy
Duration: 1 Aug 20192 Aug 2019
http://www.statmt.org/wmt19/

Conference

ConferenceACL 2019 Fourth Conference on Machine Translation
Abbreviated titleWMT19
CountryItaly
CityFlorence
Period1/08/192/08/19
Internet address

Fingerprint Dive into the research topics of 'CUNI System for the WMT19 Robustness Task'. Together they form a unique fingerprint.

Cite this