The effectiveness and implications of language localization with machine translation in mobile-assisted language learning

Abstract

Mobile-assisted language learning (MALL) and machine translation (MT) as the typical language representation and processing applications in humans and machines, respectively, have garnered significant attention over the past two decades owing to the rapid advancements in artificial intelligence. However, there remains a notable absence of investigation into the relationship between MT and foreign language teaching and learning. One of the surprising absences is the investigation of the role(s) of MT beyond the language classroom—how MT can help learners actively and autonomously learn a foreign language. This study posits that MALL applications leverage MT as foundational elements of human language learning, thereby raising issues pertaining to usability and localization. In applications of this type, learning happens via translation-based activities while evaluation is performed by comparing learners’ responses to a large set of human-acceptable translations. Employing a mixed-methods research approach, this study employs Duolingo as a case study to assess the effectiveness of MALL application localization with MT. The implications of the findings are discussed, offering insights for researchers and MALL developers seeking to enhance the integration of MT. This inquiry aims to contribute to the ongoing improvement and refinement of MALL applications. Meanwhile, by examining the user experiences of MALL application users, the study seeks to elucidate the impact of localization challenges on learner motivation and effectiveness.