LMU Munich's Neural Machine Translation Systems for News
            Articles and Health Information Texts

Huck, Matthias; Braune, Fabienne; Fraser, Alexander

doi:10.18653/v1/w17-4730

Cited by 11 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chinese is tokenized by Chinese characters and the vocabulary size is 10K. (Huck et al, 2018) For the WMT18 news translation shared task, LMU Munich (Huck et al, 2018) has trained ba-sic shallow attentional encoder-decoder systems (Bahdanau et al, 2014) with the Nematus toolkit (Sennrich et al, 2017), like last year (Huck et al, 2017a). LMU has participated with these NMT systems for the English-German language pair in both translation directions.…”

Section: Li-muzementioning

confidence: 99%

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

268

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: Li-muzementioning

confidence: 99%

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

268

223

View full text Add to dashboard Cite

show abstract

“…We refer the reader to the system description paper (Huck et al, 2017a), where we include some interesting translation examples from the news translation task. We note that our system was ranked first in the human evaluation of the news task, despite having a lower BLEU score than Edinburgh's submission.…”

Section: Discussionmentioning

confidence: 99%

Target-side Word Segmentation Strategies for Neural Machine Translation

Huck¹,

Rieß²,

Fraser³

2017

Proceedings of the Second Conference on Machine Translation

Self Cite

View full text Add to dashboard Cite

For efficiency considerations, state-of-theart neural machine translation (NMT) requires the vocabulary to be restricted to a limited-size set of several thousand symbols. This is highly problematic when translating into inflected or compounding languages. A typical remedy is the use of subword units, where words are segmented into smaller components. Byte pair encoding, a purely corpus-based approach, has proved effective recently.In this paper, we investigate word segmentation strategies that incorporate more linguistic knowledge. We demonstrate that linguistically informed target word segmentation is better suited for NMT, leading to improved translation quality on the order of magnitude of +0.5 BLEU and −0.9 TER for a medium-scale English→German translation task.Our work is important in that it shows that linguistic knowledge can be used to improve NMT results over results based only on the language-agnostic byte pair encoding vocabulary reduction technique.

show abstract

“…In order to reduce the vocabulary size, on the German MT output and post-edits we apply our reimplementation of the word segmentation method introduced by Huck et al (2017). It consists of three different steps:…”

Section: Data Pre-processingmentioning

confidence: 99%

“…2. The output of the previous step is passed to the empirical compound splitter described in (Koehn and Knight, 2003), which is run with the same parameters reported in (Huck et al, 2017);…”

Section: Data Pre-processingmentioning

confidence: 99%

Multi-source transformer with combined losses for automatic post editing

Tebbifakhr¹,

Agrawal²,

Negri³

et al. 2018

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

View full text Add to dashboard Cite

Recent approaches to the Automatic Postediting (APE) of Machine Translation (MT) have shown that best results are obtained by neural multi-source models that correct the raw MT output by also considering information from the corresponding source sentence. To this aim, we present for the first time a neural multi-source APE model based on the Transformer architecture. Moreover, we employ sequence-level loss functions in order to avoid exposure bias during training and to be consistent with the automatic evaluation metrics used for the task. These are the main features of our submissions to the WMT 2018 APE shared task, where we participated both in the PBSMT subtask (i.e. the correction of MT outputs from a phrase-based system) and in the NMT subtask (i.e. the correction of neural outputs). In the first subtask, our system improves over the baseline up to-5.3 TER and +8.23 BLEU points ranking second out of 11 submitted runs. In the second one, characterized by the higher quality of the initial translations, we report lower but statistically significant gains (up to-0.38 TER and +0.8 BLEU), ranking first out of 10 submissions.

show abstract

LMU Munich's Neural Machine Translation Systems for News Articles and Health Information Texts

Cited by 11 publications

References 29 publications

Findings of the 2018 Conference on Machine Translation (WMT18)

Findings of the 2018 Conference on Machine Translation (WMT18)

Target-side Word Segmentation Strategies for Neural Machine Translation

Multi-source transformer with combined losses for automatic post editing

Contact Info

Product

Resources

About