Machine Translation Using the Universal Networking Language ( UNL )

There is a growing insight that high-quality NLP applications for information access are in need of deeper semantic analysis. Many machine translation systems have been developed in the past years. However, these systems faced many problems, some of which are: lexical ambiguity, syntactic ambiguity, referential ambiguity and differences in conceptual specificity. Machine translation has been brought to a large public by tools available on the Internet, such as Google, AltaVista, and by low-cost programs such as Babylon. These tools produce a "gisting translation" — a rough translation that "gives the gist" of the source text, but is not otherwise usable. MT systems can produce translations more quickly and often more cheaply than human translators; however, in the majority of cases, the quality of MT is inferior to the quality of human translation (HT). An automatic semantic translation could be closer in quality somehow to the quality of an HT. Most machine Translation (MT) systems represent a machine translation as an automatic process that translates from one human language to another language by using context information. However, if the translation stems from a semantic representation the situation will be different.