Although handcrafted content from our language experts lies at the heart and soul of our offering, Babbel is constantly looking at ways to enhance the experience of our users through cutting-edge technology. For this reason, we are actively involved in the international scientific community, so that we can stay up to date with the latest technological developments. We also conduct our own research in how to apply computational linguistics methodologies to language learning applications. Our computational linguistics team recently presented original research at the 12th Workshop on Innovative Use of NLP for Building Educational Applications (BEA12) in Copenhagen, Denmark.
The BEA12 workshop focused on ways to use natural language processing (NLP) technology in educational applications, including error detection and correction, automated essay scoring, annotation and databases, and dialogue systems. This year only 9 papers out of 62 submissions were selected as oral presentations and we were lucky enough to be one of them. The BEA12 workshop was part of the larger Empirical Methods in Natural Language Processing (EMNLP) conference, organized by the Association for Computational Linguistics (ACL).
Our paper describes a prototype created by Babbel’s computational linguistics team that harnesses the power of linked data for language-learning applications, proposing new methods for creating learning content and analyzing existing learning content. Linked data and the Semantic Web are ideas that Tim Berners-Lee, the inventor of the World Wide Web, has been championing since the turn of the century, and for which there is now a suite of technology available. The Semantic Web is the idea of turning the current internet, a web of documents, into a web of data, creating the Giant Global Graph, or Web 3.0. Although we don’t have a Semantic Web yet, the principles and technologies of the Semantic Web can be used for other purposes, like creating a knowledge base around Babbel’s learning content that is filled with linguistic annotation and other linguistic resources.
For the hardcore nerds who want to find out more, the paper is available via the ACL’s website.