The authors discuss both the proper use of available online machine translation (MT) technologies for law library users and their comparative evaluation of the performance of a number of representative online MT systems in translating legal texts from various languages into English. They evaluated a large-scale corpus of legal texts by means of BLEU/NIST scoring, a de facto standard way of exercising translation-quality evaluation in the field of MT in recent years and a method that provides an objective view of the suitability of these systems for legal translation in different language pairs.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados