LIMSI's statistical translation systems for WMT'08

Déchelotte, Daniel; Adda, Gilles; Allauzen, Alexandre; Bonneau-Maynard, Hélène; Galibert, Olivier; Gauvain, Jean‐Luc; Langlais, Philippe; Yvon, François

doi:10.3115/1626394.1626404

Cited by 12 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pre-processing of English data relies on inhouse tools (Déchelotte et al, 2008). All the Czech data were tokenized and truecased using the Moses toolkit (Koehn et al, 2007).…”

Section: Data and Preprocessingmentioning

confidence: 99%

Limsi$@$wmt'17

Burlot

Safari

Labeau

et al. 2017

Proceedings of the Second Conference on Machine Translation

Self Cite

View full text Add to dashboard Cite

This paper describes LIMSI's submissions to the news shared task at WMT'17 for English into Czech and Latvian, as well as related experiments. This year's novelties consist in the use of a neural machine translation system with a factored output predicting simultaneously a lemma decorated with morphological information and a fine-grained part-of-speech. Such a type of system drew our attention to the specific step of reinflection, where lemmas and parts-of-speech are transformed into fully inflected words. Finally, we ran experiments showing an efficient strategy for parameter initialization, as well as data filtering procedures.

show abstract

“…The pre-processing of English data relies on inhouse tools (Déchelotte et al, 2008). All the Czech data were tokenized and truecased using the Moses toolkit (Koehn et al, 2007).…”

Section: Data and Preprocessingmentioning

confidence: 99%

Limsi$@$wmt'17

Burlot

Safari

Labeau

et al. 2017

Proceedings of the Second Conference on Machine Translation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Tokenization for English text relies on in-house text processing tools (Déchelotte et al, 2008). For the Russian corpora, we used the TreeTagger tokenizer.…”

Section: Data Pre-processing and Word Alignmentsmentioning

confidence: 99%

LIMSI$@$WMT’16: Machine Translation of News

Allauzen¹,

Aufrant²,

Burlot³

et al. 2016

Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

Self Cite

View full text Add to dashboard Cite

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 target word order.

show abstract

“…The preprocessing of English data relies on in-house tools (Déchelotte et al, 2008). All the Czech data were tokenized and truecased the Moses toolkit (Koehn et al, 2007).…”

Section: Data and Preprocessingmentioning

confidence: 99%

Word Representations in Factored Neural Machine Translation

Burlot¹,

García-Martínez²,

Barrault³

et al. 2017

Proceedings of the Second Conference on Machine Translation

Self Cite

View full text Add to dashboard Cite

Translation into a morphologically rich language requires a large output vocabulary to model various morphological phenomena, which is a challenge for neural machine translation architectures. To address this issue, the present paper investigates the impact of having two output factors with a system able to generate separately two distinct representations of the target words. Within this framework, we investigate several word representations that correspond to different distributions of morpho-syntactic information across both factors. We report experiments for translation from English into two morphologically rich languages, Czech and Latvian, and show the importance of explicitly modeling target morphology.

show abstract

LIMSI's statistical translation systems for WMT'08

Cited by 12 publications

References 8 publications

Limsi$@$wmt'17

Limsi$@$wmt'17

LIMSI$@$WMT’16: Machine Translation of News

Word Representations in Factored Neural Machine Translation

Contact Info

Product

Resources

About