We present a novel paradigm for statistical machine translation (SMT), based on a joint modeling of word alignment and the topical aspects underlying bilingual document-pairs, via...
We present the Prolog Cafe system that translates Prolog into Java via the WAM. Prolog Cafe provides multi-threaded Prolog engines. A Prolog Cafe thread seem to be conceptually an ...
The aim of the work is twofold. In order to face the problem of modeling time constraints in Promela, a timed extension of the language is presented. Next, timed Promela is transla...
We explore how to improve machine translation systems by adding more translation data in situations where we already have substantial resources. The main challenge is how to buck ...
In this paper, we introduce a method that automatically builds text classifiers in a new language by training on already labeled data in another language. Our method transfers the...