Named entity recognition refers to a task of automatic extraction of certain types of entities (e.g. names of people, organisations, locations, etc.) from text. The simplest approach to NER is to simply match text against a predefined dictionary of names of interest. The problem with this method, though, is that dictionaries are often not comprehensive and direct text-matching can be imprecise due to word form variation. Your task is to implement an efficient method for dictionary based NER applied to estonian text.