Logo Logo
Hilfe
Hilfe
Switch Language to English

Stojanovski, Dario; Hangya, Viktor; Huck, Matthias und Fraser, Alexander (2019): The LMU Munich Unsupervised Machine Translation System for WMT19. In: Fourth Conference on Machine Translation (Wmt 2019): S. 393-399

Volltext auf 'Open Access LMU' nicht verfügbar.

Abstract

We describe LMU Munich's machine translation system for German -> Czech translation which was used to participate in the WMT19 shared task on unsupervised news translation. We train our model using monolingual data only from both languages. The final model is an unsupervised neural model using established techniques for unsupervised translation such as denoising autoencoding and online back-translation. We bootstrap the model with masked language model pretraining and enhance it with back-translations from an unsupervised phrase-based system which is itself bootstrapped using unsupervised bilingual word embeddings.

Dokument bearbeiten Dokument bearbeiten