Search Results for author:
Found 14 papers, 2 papers with code
Two-Step MT: Predicting Target Morphology
This paper describes a two-step machine translation system that addresses the issue of translating into a morphologically rich language (English to Czech), by performing separately the translation and the generation of target morphology.
Lingua Custodia at WMT'19: Attempts to Control Terminology
This paper describes Lingua Custodia's submission to the WMT'19 news shared task for German-to-French on the topic of the EU elections.
Using Monolingual Data in Neural Machine Translation: a Systematic Study
Our findings confirm that back-translation is very effective and give new explanations as to why this is the case.
The WMT'18 Morpheval test suites for English-Czech, English-German, English-Finnish and Turkish-English
Progress in the quality of machine translation output calls for new automatic evaluation procedures and metrics.
\'Evaluation morphologique pour la traduction automatique : adaptation au fran\ccais (Morphological Evaluation for Machine Translation : Adaptation to French)
Le nouvel {\'e}tat de l{'}art en traduction automatique (TA) s{'}appuie sur des m{\'e}thodes neuronales, qui diff{\'e}rent profond{\'e}ment des m{\'e}thodes utilis{\'e}es ant{\'e}rieurement.
Normalisation automatique du vocabulaire source pour traduire depuis une langue \`a morphologie riche (Learning Morphological Normalization for Translation from Morphologically Rich Languages)
Lorsqu{'}ils sont traduits depuis une langue {\`a} morphologie riche vers l{'}anglais, les mots-formes sources contiennent des marques d{'}informations grammaticales pouvant {\^e}tre jug{\'e}es redondantes par rapport {\`a} l{'}anglais, causant une variabilit{\'e} formelle qui nuit {\`a} l{'}estimation des mod{\`e}les probabilistes.
