New Grammar of Contemporary Standard Slovene: Sources and Methods
Keywords:
contemporary Slovene, grammatical data, corpus linguistics, machine extraction, open digital databasesSynopsis
The monograph "New Grammar of Contemporary Standard Slovene: Sources and Methods" was created as part of the national basic research project of the same name (Slovenian Research Agency, 2017-2020) and presents project results of three different types: new procedures for machine extraction of linguistic data from the Gigafida and GOS reference corpora (contemporary written and spoken Slovene), a new tool for user-friendly export of corpus data, and open-access databases with information from different linguistic levels. The new procedures and data are useful for a variety of purposes, from linguistic research to machine processing of contemporary Slovene, and ultimately for a corpus-based grammatical description of contemporary Slovene.
Chapters
-
Predgovor
-
Analize za nadgradnjo učnega korpusa ssj500k
-
Zasnova in uporaba korpusnega luščilnika LIST
-
Oblikoslovni vzorci za strojno procesiranje slovenščine
-
Strojno luščenje medbesednih povezav v oblikoslovnem leksikonu Sloleks 2.0
-
Opis modela za pridobivanje in strukturiranje kolokacijskih podatkov iz korpusa
-
Zapis kanonične oblike frazeoloških enot v Leksikonu večbesednih enot za slovenščino
-
Strojno prepoznavanje idiomov z globokimi nevronskimi mrežami
-
Strojno berljiv Vezljivostni leksikon slovenskih glagolov
-
Leksikon formulaičnih besednih nizov v pisni in govorjeni slovenščini