Naslov
Typological Approach to Improve Dependency Parsing for Croatian Language
(Typological Approach to Improve Dependency Parsing for Croatian Language)

Autori
Alves, Diego ; Bekavac, Božo ; Tadić, Marko

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 20th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2021) / Dakota, Daniel ; Evang, Kilian ; Kübler, Sandra - Sofija : Association for Computational Linguistics (ACL), 2021, 1-11

ISBN
978-1-955917-16-2

Skup
20th International Workshop on Treebanks and Linguistic Theories (TLT 2021)

Mjesto i datum
Online, 21.03.2022. - 24.03.2022

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
dependency parsing ; typology ; Croatian ; multilingualism

Sažetak
This article presents the results of the experiments concerning different typological approaches considering syntactic structures with the aim to identify similar languages which can be com- bined with Croatian to improve UAS and LAS metrics when using a deep learning tool. From the eight selected languages coming from different linguistic families and genera, we showed that Slovene and Irish are the best candidates which improved significantly dependency parsing results. Slovak is the only language presenting negative synergy when combined with Croat- ian. Both typological approaches presented in this study, using quantitative data concerning rules from context-free grammar extracted from corpora using Marsagram tool and using syntactic features from lang2vec language vectors, did not allow us to explain the observed synergy when the different languages were combined. The traditional genealogical classification does not ex- plain either the improvement provided by Irish or the negative impact of the Slovak language in both considered metrics.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti, Filologija

POVEZANOST RADA