Application of OSTIA to Machine Translation Tasks

A new application of the Onward Subsequential Transducer Inference Algorithm (OSTIA) is presented. Limited-domain Machine Translation tasks have been defined from a conceptually constrained task which was recently proposed within the field of Cognitive Science. Large corpora of English-to-Spanish and English-to-German translations have been generated, and exhaustive experiments have been carried out to test the ability of OSTIA to learn these translations. The success of the results show the usefulness of formal learning techniques in limited-domain Machine Translation tasks.