EU-BRIDGE MT: Combined Machine Translation

By Markus Freitag, Stephan Peitz, Joern Wuebker, Hermann Ney, Matthias Huck, Rico Sennrich, Nadir Durrani, Maria Nadejde, Philip Williams, Philipp Koehn and 3 more. 2014

23 citations recorded by the source corpus.

This paper describes one of the collaborative efforts within EU-BRIDGE to further advance the state of the art in machine translation between two European language pairs, German→English and English→German. Three research institutes involved in the EU-BRIDGE project combined their individual machine translation systems and participated with a joint setup in the shared translation task of the evaluation campaign at the ACL 2014 Eighth Workshop on Statistical Machine Translation (WMT 2014). We combined up to nine different machine translation engines via system combination. RWTH Aachen University, the University of Edinburgh, and Karlsruhe Institute of Technology developed several individual systems which serve as system combination input. We devoted special attention to building syntax-based systems and combining them with the phrasebased ones. The joint setups yield empirical gains of up to 1.6 points in BLEU and 1.0 points in TER on the WMT newstest2013 test set compared to the best single systems.

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

Edinburgh’s Phrase-based Machine Translation Systems for WMT-14 (2014, methodology): “Our German-English constrained systems were used for EU-Bridge system combination, a collaborative effort to improve the state-of-the-art in machine translation (See Freitag et al. (2014)”
On Using Very Large Target Vocabulary for Neural Machine Translation (2014, neutral): “This is supported by the fact that higher cross-model BLEU scores (Freitag et al., 2014) are observed for models that were partially trained together.”
A Character-level Decoder without Explicit Segmentation for Neural Machine Translation (2016, neutral): “(1) Freitag et al. (2014). (2, 6) Williams et al.”
The Edinburgh/LMU Hierarchical Machine Translation System for WMT 2016 (2016, background): “4 The QT21/HimL submission highlights the continued success of system combinations based on the Jane machine translation toolkit (Freitag et al., 2014a) in open evaluation campaigns (Freitag et al., 2013; Freitag et al., 2014b; Freitag et al., 2014c).”
The RWTH Aachen German-English Machine Translation System for WMT 2014 (2014, methodology): “Both phrase-based and hierarchical phrase-based ﬁnal systems are used in the EU-Bridge sys-tem combination (Freitag et al., 2014).”
The RWTH Aachen University English-Romanian Machine Translation System for WMT 2016 (2016, background): “Combining several single machine translation engines has proven to be highly effective in previous sub-missions, e.g. (Freitag et al., 2013; Freitag et al., 2014a; Peter et al., 2015).”
Combined spoken language translation (2014, background): “Similar cooperative approaches based on system combination have proven to be valuable for machine translation in previous joint submissions, e.g. [4, 5].”