CUNI-Bergamot Submission at WMT22 General Task

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10457006" target="_blank" >RIV/00216208:11320/22:10457006 - isvavai.cz</a>

Result on the web

<a href="https://www.statmt.org/wmt22/pdf/2022.wmt-1.21.pdf" target="_blank" >https://www.statmt.org/wmt22/pdf/2022.wmt-1.21.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

CUNI-Bergamot Submission at WMT22 General Task

Original language description

We present CUNI-Bergamot submission for WMT22 General translation task. We compete in English → Czech direction. Our submission further explores block backtranslation techniques. In addition to the previous work, we measure performance in terms of COMET score and named entities translation accuracy. We evaluate performance of MBR decoding compared to traditional mixed backtranslation training and we show possible synergy when using both of the techniques simultaneously. The results show that both approaches are effective means of improving translation quality and they yield even better results when combined.

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

<a href="/en/project/GX19-26934X" target="_blank" >GX19-26934X: Neural Representations in Multi-modal and Multi-lingual Modeling</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2022

Confidentiality

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