Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that multilingual NMT requires stro...

ESS ERIC in collaboration with Sciences Po decided to develop a Web Panel Sample Service as part of the SSHOC project. This software will be used by ESS ERIC for CRONOS-2, a cross-national panel, as part of ESS-SUSTAIN-2 H2020 project. This presentation outlines the mai...

For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally evaluated with standard autom...

Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work aims to answer two questions: 1) ...

This paper describes the Arabic Multi-Genre Broadcast (MGB-2) Challenge for SLT-2016. Unlike last year's English MGB Challenge, which focused on recognition of diverse TV genres, this year, the challenge has an emphasis on handling the diversity in dialect in Arabic spe...

This paper describes the AMU-UEDIN submissions to the WMT 2016 shared task on news translation. We explore methods of decode-time integration ofattention-based neural translation models with phrase-based statistical machinetranslation. Efficient batch-algorithms for GPU...