The University of Helsinki submissions to the WMT19 news translation task
This work addresses machine translation challenges for specific language pairs, but it is incremental as it builds on existing methods and shared tasks.
The paper tackled the WMT19 news translation task by cleaning training data and exploring various translation models for three language pairs, achieving improved results through data filtering and model comparisons.
In this paper, we present the University of Helsinki submissions to the WMT 2019 shared task on news translation 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 and 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.