Fault-tolerant (FT) distributed protocols (such as group membership, consensus, etc.) represent fundamental building blocks for many practical systems, e.g., the Google File System...
We improve the quality of statistical machine translation (SMT) by applying models that predict word forms from their stems using extensive morphological and syntactic information...
Universidade de ´Evora’s Integrated Information System (SIIUE) aims at representing the entire universe of concepts useful for the management and day-to-day operation of the Or...
We introduce factored language models (FLMs) and generalized parallel backoff (GPB). An FLM represents words as bundles of features (e.g., morphological classes, stems, data-drive...