The development of a comprehensive morphological dictionary of multi-word units for Serbian is a very demanding task, due to the complexity of Serbian morphology. Manual production of such a dictionary proved to be extremely time-consuming. In this paper we present a procedure that automatically produces dictionary lemmas for a given list of multi-word units. To accomplish this task the procedure relies on data in e-dictionaries of Serbian simple words, which are already well developed. We also offer an evaluation ...
... conditions. As for the inflection of constituent
simple words, it relies completely on FSTs for the inflection of simple words.
This way, the generation of all inflected forms with Multiflex is performed with
two types of FSTs: for inflection of simple words and for inflection of MWUs. To
that end, a ...
... for both monolingual and multi-lingual search. The main feature of
WS4QE is that it enables inflection of simple words and MWUs supplied as key-
words to Google. Again, Unitex and Multiflex are used for inflection. However,
WS4QE goes one step further: for free phrases supplied as key-words having a
structure ...
... some implementation issues
and present how the same procedure is used for other languages.
Key words: electronic dictionary, Serbian, morphology, inflection, multi-
word units, noun phrases, query expansion
1 Introduction
We have been developing morphological electronic dictionaries of Serbian for
natural ...
Cvetana Krstev, Ranka Stanković, Ivan Obradović, Duško Vitas, Miloš Utvić. "Automatic construction of a morphological dictionary of multi-word units" in Lecture Notes in Computer Science 6233, Advances in Natural Language Processing, Proceedings of the 7thInternational Conference on NLP, IceTAL 2010, Reykjavik, Iceland, August 2010, Springer (2010): 226-237. https://doi.org/10.1007/978-3-642-14770-8_26
