Web application for foreign vocabulary learning based on cross-lingual etymological linked data

The thesis will focus on developing a web application that helps create a passive vocabulary in some foreign languages. This thesis plans to explore how the etymological relations between languages could be used to grow a user's passive vocabulary. Linked Data will be used as a source of word pairs. The thesis will measure how successfully such proposed word pairs could be learned based on the etymological knowledge graph, i.e., having common roots despite surface differences. The web application will use linked linguistic data as a database and some heuristic algorithms for better word ordering and a smoother learning process. The thesis will not include Linked Data database creation but will use an existing one. Data quality is a crucial requirement that can significantly affect the final evaluation. The application will provide a learn section where the user can pick word pairs that are worth learning and a test section where the user can test the knowledge. Based on the evaluation and the success rate provided by the web application, the thesis will try to investigate whether it is possible to grow a passive vocabulary in a foreign language based on etymological links between words in a foreign language and the words in language users already know. The work-in-progress name for the website is Linked Languages.