Combining Word Reordering Methods on different Linguistic Abstraction Levels for Statistical Machine Translation

By Teresa Herrmann, Jan Niehues, A. Waibel. 2013

34 citations recorded by the source corpus.

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

Findings of the 2016 Conference on Machine Translation (2016, methodology): “(28)It consists of a phrase-based machine translation system leveraging generic and in-domain parallel training data and using a pre-reordering technique (Herrmann et al., 2013).”
Findings of the 2017 Conference on Machine Translation (WMT17) (2017, methodology): “We used phrase-based MT systems trained with generic and in-domain parallel training data, leveraging prereordering techniques (Herrmann et al., 2013), and taking advantage of POS and word class-based language models.”
EU-BRIDGE MT: Combined Machine Translation (2014, methodology): “In addition, a tree-based re-ordering model (Herrmann et al., 2013) trained on syntactic parse trees (Rafferty and Manning, 2008b; Klein and Manning, 2003) as well as a lex-icalized reordering model (Koehn et al., 2005) are applied.”
The Karlsruhe Institute of Technology Translation Systems for the WMT 2015 (2015, background): “The differences in word order between German and English can be better addressed by us-ing a tree-based reordering model as shown in Herrmann et al. (2013).”
The KIT-LIMSI Translation System for WMT 2015 (2015, methodology): “Additionally, a tree-based reordering model (Herrmann et al., 2013) trained on syntactic parse trees (Klein and Manning, 2003) is applied to the source side to better address the differences in word order be-tween English and German.”
Combined spoken language translation (2014, methodology): “Long-range rules [48] and tree-based reordering rules [49] were used for German→English.”
The Karlsruhe Institute of Technology Translation Systems for the WMT 2014 (2014, methodology): “In addition, we apply a tree-based reordering model (Herrmann et al., 2013) to better address the differences in word order between German and English.”
Pre-Translation for Neural Machine Translation (2016, methodology): “The advanced system use pre-reodering (Herrmann et al., 2013) and lexicalized reordering.”
The KIT-LIMSI Translation System for WMT 2014 (2014, methodology): “In addition, a tree-based reordering model (Herrmann et al., 2013) trained on syntactic parse trees (Rafferty and Manning, 2008; Klein and Manning, 2003) is applied to the source sentence.”