Pregled bibliografske jedinice broj: 1273980
Corpus-based Syntactic Typological Methods for Dependency Parsing Improvement
Corpus-based Syntactic Typological Methods for Dependency Parsing Improvement // Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP (SIGTYP 2023) / Vylomova, Ekaterina (ur.).
Stroudsburg, PA (USA): ACL, 2023. str. 76-88
CROSBI ID: 1273980 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Corpus-based Syntactic Typological Methods for
Dependency Parsing Improvement
Autori
Alves, Diego ; Bekavac, Božo ; Zeman, Daniel ; Tadić, Marko
Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni
Knjiga
Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP (SIGTYP 2023)
Urednik/ci
Vylomova, Ekaterina
Izdavač
ACL
Grad
Stroudsburg, PA (USA)
Godina
2023
Raspon stranica
76-88
ISBN
978-1-959429-56-2
Ključne riječi
corpus-based typology ; dependency parsing ; multilingualism
Sažetak
This article presents a comparative analysis of four different syntactic typological approaches applied to 20 different languages to determine the most effective one to be used for the improvement of dependency parsing results via corpora combination. We evaluated these strategies by calculating the correlation between the language distances and the empirical LAS results obtained when languages were combined in pairs. From the results, it was possible to observe that the best method is based on the extraction of word order patterns which happen inside subtrees of the syntactic structure of the sentences.
Izvorni jezik
Engleski
Znanstvena područja
Interdisciplinarne humanističke znanosti
POVEZANOST RADA
Projekti:
EK-H2020-812997 - Cross-lingual Event-centric Open Analytics Research Academy (Cleopatra) (Tadić, Marko, EK - H2020-MSCA-ITN-2018) ( CroRIS)
Ustanove:
Filozofski fakultet, Zagreb
