Multilingual Knowledge-Based Concept Recognition in Textual Data

With respect to the increasing volume of textual data which is available through digital resources today, the identification of the main concepts in those texts becomes increasingly important and can be seen as a vital step in the analysis of unstructured information. Research in this area has focused on the detection of named entities like person names or organization names, which only cover a very small part of concepts in texts. Especially the unique mapping between concepts in different languages requires parallel corpora, which are rarely available in industrial settings. We therefore propose a powerful new knowledge based model to recognize various kinds of concepts even in very short and specialized texts using linguistic information for synonym handling and word sense disambiguation. We evaluate the proposed model on texts from the automotive domain.