LIMSI@WMT’16: Machine Translation of News
By Alexander Allauzen, Lauriane Aufrant, Franck Burlot, Ophélie Lacroix, Elena Knyazeva, Thomas Lavergne, Guillaume Wisniewski, François Yvon. 2016
12 citations recorded by the source corpus.
This paper describes LIMSI’s submissions to the shared WMT’16 task “Translation of News”. We report results for Romanian-English in both directions, for English to Russian, as well as preliminary experiments on reordering to translate from English into German. Our submissions use mainly NCODE and MOSES along with continuous space models in a post-processing step. The main novelties of this year’s participation are the following: for the translation into Russian and Romanian, we have attempted to extend the output of the decoder with morphological variations and to use a CRF model to rescore this new search space; as for the translation into German, we have been experimenting with source-side pre-ordering based on a dependency structure allowing permutations in order to reproduce the tar- get word order.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Ondrej Bojar
- Philipp Koehn
- Rico Sennrich
- Yonatan Belinkov
- Barry Haddow
- Felix Stahlberg
- Nadir Durrani
- Graham Neubig
Citations in the corpus
- Findings of the 2016 Conference on Machine Translation (2016, neutral): “LIMSI University of Paris (Allauzen et al., 2016)”
- The Edinburgh/LMU Hierarchical Machine Translation System for WMT 2016 (2016, methodology): “The target side of the data is preprocessed with tokro, LIMSI’s tokenizer for Romanian (Allauzen et al., 2016).”
- The QT21/HimL Combined Machine Translation System (2016, methodology): “On the Romanian side, the data is tokenized using LIMSI’s tokro (Allauzen et al., 2016), a rulebased tokenizer that mainly normalizes diacritics and splits punctuation and clitics.”