This paper describes the University of Helsinki’s submissions to the WMT18 shared news translation task for English-Finnish and English-Estonian, in both directions. This year, our main submissions employ a novel neural architecture, the Transformer, using the open-source OpenNMT framework. Our experiments couple domain labeling and fine tuned multilingual models with shared vocabularies between the source and target language, using the provided parallel data of the shared task and additional back-translations. Finally, we compare, for the English-to-Finnish case, the effectiveness of different machine translation architectures, starting from a rule-based approach to our best neural model, analyzing the output and highlighting future research.

Raganato, A., Scherrer, Y., Nieminen, T., Hurskainen, A., Tiedemann, J. (2018). The University of Helsinki submissions to the WMT18 news task. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers (pp.488-495). Association for Computational Linguistics (ACL) [10.18653/v1/W18-6425].

The University of Helsinki submissions to the WMT18 news task

Raganato, Alessandro
;
2018

Abstract

This paper describes the University of Helsinki’s submissions to the WMT18 shared news translation task for English-Finnish and English-Estonian, in both directions. This year, our main submissions employ a novel neural architecture, the Transformer, using the open-source OpenNMT framework. Our experiments couple domain labeling and fine tuned multilingual models with shared vocabularies between the source and target language, using the provided parallel data of the shared task and additional back-translations. Finally, we compare, for the English-to-Finnish case, the effectiveness of different machine translation architectures, starting from a rule-based approach to our best neural model, analyzing the output and highlighting future research.
Si
paper
Scientifica
machine translation; transformer; multilinguality
English
3rd Conference on Machine Translation, WMT 2018 at the Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
978-194808781-0
Raganato, A., Scherrer, Y., Nieminen, T., Hurskainen, A., Tiedemann, J. (2018). The University of Helsinki submissions to the WMT18 news task. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers (pp.488-495). Association for Computational Linguistics (ACL) [10.18653/v1/W18-6425].
Raganato, A; Scherrer, Y; Nieminen, T; Hurskainen, A; Tiedemann, J
File in questo prodotto:
File Dimensione Formato  
W18-6425.pdf

Solo gestori archivio

Dimensione 127.25 kB
Formato Adobe PDF
127.25 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/361563
Citazioni
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
Social impact