The University of Helsinki submissions to the WMT18 news task

Raganato, Alessandro; Scherrer, Yves; Nieminen, Tommi; Hurskainen, Arvi; Tiedemann, Jörg

doi:10.18653/v1/w18-6425

Cited by 3 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HY-AH (Raganato et al, 2018;Hurskainen and Tiedemann, 2017) is a rule-based machine translation system, relying on a rule-based dependency parser for English, a hand-crafted translation lexicon (based on dictionary data extracted from parallel corpora by word alignment), various types of transfer rules, and a morphological generator for Finnish.…”

Section: Gtcommentioning

confidence: 99%

“…HY-NMT (Raganato et al, 2018) submissions are based on the Transformer "base" model, trained with all the parallel data provided by the shared task plus back-translations, with a shared vocabulary between source and target language and a domain label for each source sentence. For the multilingual sub-track synthetic data for English→Estonian and Estonian→English was also used.…”

Section: Gtcommentioning

confidence: 99%

“…The final system is trained with four different seeds and mixed data. (Raganato et al, 2018;Hurskainen and Tiedemann, 2017) The University of Helsinki (HY) submitted four systems: HY-AH, HY-NMT, HY-NMT-2STEP and HY-SMT.…”

Section: Alibaba (mentioning

confidence: 99%

See 2 more Smart Citations

Findings of the 2018 Conference on Machine Translation (WMT18)

Bojar¹,

Federmann²,

Fishel³

et al. 2018

Proceedings of the Third Conference on Machine Translation: Shared Task Papers

269

223

View full text Add to dashboard Cite

This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2018. Participants were asked to build machine translation systems for any of 7 language pairs in both directions, to be evaluated on a test set of news stories. The main metric for this task is human judgment of translation quality. This year, we also opened up the task to additional test sets to probe specific aspects of translation. Language Sources (Number of Documents) English ABC News (1), BBC (4), Brisbane Times (1), CBS News (1), Daily Mail (4), Euronews (3), Globe and Mail (1), Guardian (4), Independent (4), Los Angeles Times (4), MSNBC (3), Novinte (2), New York Times (2), Reuters (3), Russia Today (2), Scotsman (2), Sydney Morning Herald (2), Telegraph (2), The Local (2), Time Magazine (2), UPI (1), Washington Post (3) Czech blesk.cz (16), deník.cz (5), Deník Referendum (1), DNES.cz (7), lidovky.cz (6), Novinky.cz (3), Reflex (2), tyden.cz (12), ZDN (2) German Aachener Nachrichten (1), Abendzeitung Nürnberg (2), Braunschweiger Zeitung (1

show abstract

Section: Gtcommentioning

confidence: 99%

Section: Gtcommentioning

confidence: 99%

See 1 more Smart Citation

Findings of the 2018 Conference on Machine Translation (WMT18)

Bojar¹,

Federmann²,

Fishel³

et al. 2018

Proceedings of the Third Conference on Machine Translation: Shared Task Papers

269

223

View full text Add to dashboard Cite

show abstract

“…For English and Finnish respectively, we trained truecaser models on all English and Finnish monolingual data as well as the English and Finnish side of all parallel English-Finnish datasets. As we had found to be optimal in our previous year submission ( Raganato et al, 2018), we trained a BPE model using a vocabulary of 37 000 symbols, trained jointly only on the parallel data. Furthermore, for some experiments, we also used domain labeling.…”

Section: Pre-processingmentioning

confidence: 99%

The University of Helsinki Submissions to the WMT19 News Translation Task

Talman¹,

Sulubacak²,

Vázquez³

et al. 2019

Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…We trained the segmentation models only on the available parallel datasets for each language pair, following the findings of our submission to the WMT18 translation task (Raganato et al, 2018). We specified a vocabulary size of 5,000 tokens for each language and we took advantage from the tokenizer integrated in the SentencePiece implementation (Kudo and Richardson, 2018) by training the models on non-tokenized data.…”

Section: Sentencepiece Unigram Modelsmentioning

confidence: 99%

The University of Helsinki Submissions to the WMT19 Similar Language Translation Task

Scherrer¹,

Vázquez²,

Virpioja³

2019

Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)

Self Cite

View full text Add to dashboard Cite

This paper describes the University of Helsinki Language Technology group's participation in the WMT 2019 similar language translation task. We trained neural machine translation models for the language pairs Czech ↔ Polish and Spanish ↔ Portuguese. Our experiments focused on different subword segmentation methods, and in particular on the comparison of a cognate-aware segmentation method, Cognate Morfessor, with character segmentation and unsupervised segmentation methods for which the data from different languages were simply concatenated. We did not observe major benefits from cognate-aware segmentation methods, but further research may be needed to explore larger parts of the parameter space. Character-level models proved to be competitive for translation between Spanish and Portuguese, but they are slower in training and decoding.

show abstract

The University of Helsinki submissions to the WMT18 news task

Cited by 3 publications

References 11 publications

Findings of the 2018 Conference on Machine Translation (WMT18)

Findings of the 2018 Conference on Machine Translation (WMT18)

The University of Helsinki Submissions to the WMT19 News Translation Task

The University of Helsinki Submissions to the WMT19 Similar Language Translation Task

Contact Info

Product

Resources

About