The paper describes the concept of the new Slovene lexical database which is compiled within the “Communication in Slovene” project. The database has a twofold goal: it is intended as the basis for the future compilation of different dictionaries of Slovene, both monolingual and bilingual, and as such its concept is biased towards lexicography. Secondly, it will be used for the enhancement of natural language processing tools for Slovene. The database is organized in six hierarchical levels with lexico-grammatical information which spans from simple morphological data on the top level to semantic, syntactic and collocational data on subordinate levels, with corpus examples at the bottom. Sketch Engine tool with word sketch, tickbox lexicography and GDEX modules is used to enable faster and more efficient extraction of corpus data from the 620-million word FidaPLUS corpus which is used as the source for the data in the database.
COBISS.SI-ID: 33264429
Good Dictionary Examples or GDEX is a tool in the Sketch Engine designed to help lexicographers with identifying dictionary examples by ranking sentences according to how likely they are to be good candidates. The ranking is done automatically using various syntactic and lexical features. So far, only GDEX for English has been available. This paper presents the design and evaluation of Slovene GDEX, which was used for finding good examples for the new lexical database of Slovene, one of the activities in the Communication in Slovene project. Several different GDEX configurations were designed, evaluated and compared. The evaluation involved examining sentences of lemmas belonging to different word classes. Good sentences were logged for subsequent analysis with external data-mining software, WEKA. The observed behaviour was then usedto adjust the parameters of the GDEX classifiers. We believe that the procedure of identifying features of good examples and their values, describedin this paper, can be used for the development of GDEX for any language.
COBISS.SI-ID: 33344045