LIMSI@WMT'17

Franck Burlot, Pooyan Safari, Matthieu Labeau, Alexandre Allauzen, François Yvon

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationWMT 2017 - 2nd Conference on Machine Translation, Proceedings
EditorsOndeej Bojar, Christian Buck, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Philipp Koehn, Julia Kreutzer
PublisherAssociation for Computational Linguistics (ACL)
Pages257-264
Number of pages8
ISBN (Electronic)9781945626968
Publication statusPublished - 1 Jan 2017
Externally publishedYes
Event2nd Conference on Machine Translation, WMT 2017 - Copenhagen, Denmark
Duration: 7 Sept 20178 Sept 2017

Publication series

NameWMT 2017 - 2nd Conference on Machine Translation, Proceedings

Conference

Conference2nd Conference on Machine Translation, WMT 2017
Country/TerritoryDenmark
CityCopenhagen
Period7/09/178/09/17

Fingerprint

Dive into the research topics of 'LIMSI@WMT'17'. Together they form a unique fingerprint.

Cite this