The CLASSLA-Stanza model for UD dependency parsing of standard Serbian 2.1

PID

The model for UD dependency parsing of standard Serbian was built with the CLASSLA-Stanza tool (https://github.com/clarinsi/classla) by training on the SETimes.SR training corpus (http://hdl.handle.net/11356/1200) and using the CLARIN.SI-embed.sr word embeddings (http://hdl.handle.net/11356/1789). The estimated LAS of the parser is ~89.83.

The difference to the previous version of the model is that this version uses the new version of Serbian word embeddings.

Identifier
PID	http://hdl.handle.net/11356/1835
Related Identifier	https://aclanthology.org/W19-3704/
Related Identifier	http://hdl.handle.net/11356/1260
Related Identifier	https://github.com/clarinsi/classla
Metadata Access	http://www.clarin.si/repository/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1835

Provenance
Creator	Terčon, Luka; Ljubešić, Nikola
Publisher	Jožef Stefan Institute
Publication Year	2023
Rights	Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0); https://creativecommons.org/licenses/by-sa/4.0/; PUB
OpenAccess	true
Contact	info(at)clarin.si

Representation
Language	Serbian
Resource Type	toolService
Format	text/plain; charset=utf-8; application/zip; downloadable_files_count: 2
Discipline	Linguistics