Opis valencijskih okvira hrvatskih dvoprijelaznih glagola temeljen na ovisnosnim bankama stabala

master's thesis

• Title (english): Description of valency frames of the Croatian ditransitive verbs based on dependency treebanks
• Author: Robert Sviben
• Mentor: Matea Filko (mentor)
• Committee member: Daniela Katunar (predsjednik povjerenstva)
• Committee member: Jurica Polančec (član povjerenstva)
• Committee member: Ivana Simeon (član povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of Linguistics); Zagreb
• Defense date and country: 2023-09-28, Croatia
• Scientific / art field, discipline and subdiscipline: HUMANISTIC SCIENCES; Philology; General Linguistics

Abstract

Analiza glagolskih valencijskih okvira obuhvaća opis i popis broja i vrste dopuna kojima određen glagol otvara mjesto u rečenici, odnosno kojima glagol upravlja na sintaktičkome i morfološkome planu. Nakon teorijskoga razmatranja karakteristika valencije i prijelaznosti te pregleda hrvatskih jezičnih resursa koji se na njima temelje, u ovome se radu predstavlja računalni opis glagolskih okvira koji počiva na stvarnoj jezičnoj uporabi. Kao izvor korpusnih podataka odabrana je ovisnosna banka stabala SETimes-HR, trenutačno najveći korpus za hrvatski jezik obilježen na sintaktičkoj razini, koji je označen i mrežno dostupan u sklopu projekta Universal Dependencies (https://universaldependencies.org/hr/). Na primjeru dvoprijelaznih glagola razrađen je model izvlačenja valencijskih okvira uz pomoć paketa pyconll u programskome jeziku Python. Utvrđene su pogreške kod označivanja i poteškoće pri računalnome modeliranju ovisnosne strukture glagola te su predložena rješenja za njih. Kvantitativna analiza dobivenih podataka pokazala je da su dvoprijelazni okviri rijetki u korpusu, ali da se dvoprijelazni glagoli često ostvaruju u drugim valencijskim okvirima. Naposljetku je uveden koncept sintaktičkih n-grama i kolokacija, kojima se mogu proširiti mogućnosti izvlačenja okvira i poboljšati točnost modela. Predstavljena metoda pokazala se korisnom i primjenjivom u budućim istraživanjima valencije i glagolske sintakse te razvoju jezičnih tehnologija za hrvatski jezik.

Abstract (english)

Analysis of verb valency frames includes a description and list of the number and types of arguments to which a given verb opens a place in a sentence, that is, which the verb governs on a syntactic and morphological level. After a theoretical consideration of the characteristics of valency and transitivity and an overview of Croatian language resources based on them, this paper presents a computational description of verb frames based on real language usage. As the source of corpus data, the SETimes-HR dependency treebank was selected, currently the largest corpus for the Croatian language annotated at the syntactic level, which is tagged and available online as part of the Universal Dependencies project (https://universaldependencies.org/hr/). Using the example of ditransitive verbs, a model for extracting valency frames was developed with the help of the pyconll package in the Python programming language. Annotation errors and difficulties in computational modeling of the dependent structure of the verb were identified and solutions were proposed. Quantitative analysis of the obtained data showed that ditransitive frames are rare in the corpus, but that ditransitive verbs are often realized in other valency frames. Finally, the concept of syntactic n-grams and collocations was introduced, which can extend the possibilities of frame extraction and improve the accuracy of the model. The presented method proved to be useful and applicable in future research on valency and verbal syntax, as well as in the development of language technologies for the Croatian language.

• Keywords: valencija; dvoprijelazni (ditranzitivni) glagoli; ovisnosne banke stabala; Universal Dependencies; uporabna analiza
• Keywords (english): valency; ditransitive verbs; dependency treebanks; Universal Dependencies; usage-based analysis
• Language: croatian
• URN:NBN: urn:nbn:hr:131:996157
• Study programme: Title: Linguistics (double major); specializations in: General Linguistics, Comparative Linguistics, Computational Linguistics, Aplied Linguistics and Cognitive Linguistics, Cognitive; Course: Computational Linguistics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra lingvistike (magistar/magistra lingvistike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Access restricted to students and staff of home institution
• Created on: 2023-10-01 20:44:42