Semantic processing performance of Internet machine translation systems

Abstract

The Internet has the potential to facilitate understanding across cultures and languages by removing the physical barriers to intercultural communication. One possible contributor to this development has been the recent release of freely‐available automated direct machine translation systems, such as AltaVista with SYSTRAN, which translates from English to five other European languages (French, German, Italian, Spanish and Portuguese), and vice versa. However, concerns have recently been raised over the performance of these systems, and the potential for confusion that can be created when the intended meaning of sentences is not correctly translated (i.e. semantic processing errors). In this paper, we use an iterative paradigm to examine errors associated with interlingual divergence in meaning arising from the automated machine translation of English proverbs. The need for the development of Web‐based translation systems, which have an explicit cross‐linguistic representation of meaning for successful intercultural communication, is discussed.