The University of Helsinki Submissions to the WMT19 News Translation Task

By Aarne Talman, Umut Sulubacak, Raúl Vázquez, Yves Scherrer, Sami Virpioja, Alessandro Raganato, A. Hurskainen, Jörg Tiedemann. 2019

7 citations recorded by the source corpus.

In this paper we present the University of Helsinki submissions to the WMT 2019 shared news translation task in three language pairs: English-German, English-Finnish and Finnish-English. This year we focused first on cleaning and filtering the training data using multiple data-filtering approaches, resulting in much smaller and cleaner training sets. For English-German we trained both sentence-level transformer models as well as compared different document-level translation approaches. For Finnish-English and English-Finnish we focused on different segmentation approaches and we also included a rule-based system for English-Finnish.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Beyond English-Centric Multilingual Machine Translation (2020, background): “En ↔ Fi: we report results from Talman et al. (2019) on WMT17. different bilingual models, one for each evaluation direction.”
Findings of the 2019 Conference on Machine Translation (WMT19) (2019, methodology): “The translation of the test sets was sponsored by the EU H2020 projects Bergamot and GoURMET (English-Czech and Gujarati-English respectively), by Yandex (Kazakh-English and Russian-English), Microsoft (Chinese-English and German-English), Tilde (Lithuanian-English), the University of Helsinki (Finn”