Production of morphological dictionaries of multi-word units using a multipurpose tool

In this paper we outline the use of the multipurpose software tool LeXimir in our approach to automated production of lemmas for e-dictionaries of multi-word units. Development of morphological dictionaries of MWUs is a tedious task, especially in the case of Serbian and other languages featuring complex morphological structures. After realizing that the development of such a dictionary manually is an extremely slow process, we endeavored towards a procedure aimed at automated production of MWU dictionary lemmas, which is also outlined in this paper. The procedure was subsequently implemented as a new functionality of LeXimir, and makes use of our comprehensive edictionaries of Serbian simple words. We present an evaluation of the performance of this functionality, and hence of our procedure, obtained from experiments on two types of data. Finally, we discuss some further possible applications of our procedure and LeXimir in language processing tasks.