Exploring Topics in Domestic Research on Machine Translation through Text Mining

Abstract

Machine translation (MT) has become increasingly ubiquitous in our daily lives, academia, and education. Learners use MT to understand foreign language texts, and teachers use MT in a variety of courses, such as general English and courses for international students. This study aims to investigate the trends of MT research in Korea and to identify the research topics that have been studied so far. To this end, this study collected 875 domestic MT research papers from the 1970s to the present and extracted the topics of the papers using topic modeling. This study then analyzed the temporal trends of each research topic to examine the changes in research topics and to identify their networks. This study's findings show that the number of research papers and research topics have changed significantly since the release of Google's neural machine translation in late 2016.