Efficient processing of Multi-Word Units in the course of development of morphological MWU dictionaries is not easy to achieve, especially when languages with complex morphological structures are concerned, such as Serbian. Manual development of this type of dictionaries is a tedious and extremely slow process. To alleviate this problem we turned to our multipurpose software tool, dubbed LeXimir, in the production of lemmas for e-dictionaries of multi-word units. In addition to that, we developed a procedure aimed at making ...
... inflectional properties of MWU lemmas
We have further improved the procedure for production of MWU lemmas when we
realized that the answers obtained automatically in support of manual production of
MWU lemmas can also help in detection of the syntactic composition of a MWU
and therefore indicate the ...
... constituent forms used in the
MWU lemma? For the first example they are aefs1g and fs1q, while for the
second they are akms1g and ms1q.
A fully manual production of MWU lemmas is, however, not necessary, because
possible answers to the above questions that concern MWU constituents can be
found in ...
... forthcoming period, as many new MWU lists are being prepared.
The benefits obtained by including the MWU dictionary in language processing
tasks for Serbian are already clearly visible. Besides the benefits that were to be
expected, it has been already shown that the MWU dictionary can also be very use- ...
Cvetana Krstev, Ivan Obradović, Ranka Stanković, Duško Vitas. "An Approach to Efficient Processing of Multi-Word Units" in Computational Linguistics - Applications, Studies in Computational Intelligence 458 no. 458, Berlin Heidelberg : Springer-Verlag (2013): 109-129. https://doi.org/10.1007/978-3-642-34399-5_6
