In cooperation with University of Ljubljana, Faculty of Computer and Information Science we are developing a set of tools for comparison of unstructured blocks of texts by their meaning (semantic comparison). The idea is to find similarities among texts beyond statistical analysis, containing words in the same context with the same/similar meaning and to enrich these with graphic representations. Advanced emerging technologies can be utilized to analyse, categorize and compare presented texts. Ministry of Public Administration will use such tool when preparing and updating data dictionaries and vocabularies. Same toolset can be useful in many other fields (like searching and comparing legal texts) and in different languages. Therefore the tools shall be open source and available to general public. A working prototype has already been tested (https://docker.biolab.si/?password=0d79e6ec2476357b371857118694ce24) and a full blown toolset is in phase of development.