Limsi$@$wmt'17

Abstract

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.