Given that Arabic is one of the most widely used languages in the world, the task of Arabic
Machine Translation (MT) has recently received a great deal of attention from the research …

Even though a linguistics-free sequence to sequence model in neural machine translation
(NMT) has certain capability of implicitly learning syntactic information of source sentences …

Abstract We use the Margin Infused Relaxed Algorithm of Crammer et al. to add a large
number of new features to two machine translation systems: the Hiero hierarchical …

Minimum-error-rate training (MERT) is a bottleneck for current development in statistical
machine translation because it is limited in the number of weights it can reliably optimize …

Standard decoders for neural machine translation autoregressively generate a single target
token per time step, which slows inference especially for long outputs. While architectural …

We investigate the use of hierarchical phrase-based SMT lattices in end-to-end neural
machine translation (NMT). Weight pushing transforms the Hiero scores for complete …

We show that jointly parsing a bitext can substantially improve parse quality on both sides. In
a maximum entropy bitext parsing model, we define a distribution over source trees, target …

Word reordering is one of the most difficult aspects of statistical machine translation (SMT),
and an important factor of its quality and efficiency. Despite the vast amount of research …

A principal weakness of conventional (ie, non-hierarchical) phrase-based statistical machine
translation is that it can only exploit continuous phrases. In this paper, we extend phrase …

Dependency syntax has been demonstrated highly useful for a number of natural language
processing (NLP) tasks. Typical approaches of utilizing dependency syntax include Tree …