Parallel data in the domain of interest is the key resource when training a statistical machine translation (SMT) system for a specific purpose. Since ad-hoc manual translation c...
Prasanth Kolachina, Nicola Cancedda, Marc Dymetman...
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
The MPI-2 Standard has carefully specified the interaction between MPI and usercreated threads. The goal of this specification is to allow users to write multithreaded MPI progr...
For some time now, image retrieval approaches have been developed that use low-level features, such as colour histograms, edge distributions and texture measures. What has been la...
Many machine-learning algorithms learn rules of behavior from individual end users, such as taskoriented desktop organizers and handwriting recognizers. These rules form a generat...