SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task

Abstract

This paper presents the description of 12 systems submitted to the WMT16 IT-task, covering six different languages, namely Basque, Bulgarian, Dutch, Czech, Portuguese and Spanish. All these systems were developed under the scope of the QTLeap project, presenting a common strategy. For each language two different systems were submitted, namely a phrasebased MT system built using Moses, and a system exploiting deep language engineering approaches, that in all the languages but Bulgarian was implemented using TectoMT. For 4 of the 6 languages, the TectoMT-based system performs better than the Moses-based one.

Machine translation and legal terminology

“…Rosa et al (2016) describe QTL-CHIMERA (Charles University). Gaudio et al (2016) describe the remaining QTL-* systems (partners from the QTLeap project: HF&FCUL for Portuguese, UPV/EHU for Spanish and Basque, IICT-BAS for Bulgarian, CUNI for Czech and UG for Dutch).…”

Dictionary-based Domain Adaptation of MT Systems without Retraining

“…We use two systems, Moses (Koehn et al, 2007) and TectoMT (Žabokrtský et al, 2008), as well as their combination Chimera (Bojar et al, 2013); see also a more detailed description of the Moses and TectoMT systems within the QTLeap project by Gaudio et al (2016) in these proceedings. 9 This holds even for the Chimera combination, i.e.…”