A current increasing trend in machine translation is to combine data-driven and rule-based techniques. Such combinations typically involve the hybridization of different paradigms such as, for instance, the introduction of linguistic knowledge into statistical paradigms, the incorporation of data-driven components into rulebased paradigms, or the pre-and postprocessing of either sort of translation system outputs. Aiming at bringing together researchers and practitioners from the different

more »

... disciplinary areas working in these directions, as well as at creating a brainstorming and discussion venue for Hybrid Translation approaches, the Hy-Tra initiative was born. This paper gives an overview of the Second Workshop on Hybrid Approaches to Translation (HyTra 2013) concerning its motivation, contents and outcomes.