Naslov
Cross-Lingual Dependency Parsing of Related Languages with Rich Morphosyntactic Tagsets

Autori
Agić, Željko ; Tiedemann, Jörg ; Dobrovoljc, Kaja ; Krek, Simon ; Merkler, Danijela ; Može, Sara

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

Izvornik
Proceedings of the EMNLP 2014 Workshop on Language Technology for Closely Related Languages and Language Variants / - Doha : Association for Computational Linguistics (ACL), 2014, 12-23

ISBN
978-1-937284-96-1

Skup
EMNLP 2014 Workshop on Language Technology for Closely Related Languages and Language Variants

Mjesto i datum
Doha, Katar, 25.10.2014. - 29.10.2014

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
cross-lingual parsing; dependency parsing; machine translation

Sažetak
This paper addresses cross-lingual dependency parsing using rich morphosyntactic tagsets. In our case study, we experiment with three related Slavic languages: Croatian, Serbian and Slovene. Four different dependency treebanks are used for monolingual parsing, direct cross-lingual parsing, and a recently introduced cross-lingual parsing approach that utilizes statistical machine translation and annotation projection. We argue for the benefits of using rich morphosyntactic tagsets in cross-lingual parsing and empirically support the claim by showing large improvements over an impoverished common feature representation in form of a reduced part-of-speech tagset. In the process, we improve over the previous state-of-the-art scores in dependency parsing for all three languages.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti

POVEZANOST RADA