Work

CLASSLA-Stanza: The Next Step for Linguistic Processing of South Slavic Languages

Year: 2025

Type: article

Abstract: We present CLASSLA-Stanza, a pipeline for automatic linguistic annotation of South Slavic languages, which is based on the Stanza natural language processing pipeline. We describe the main improvements in CLASSLA-Stanza with respect to Stanza and give a detailed description of the model training process for the latest 2.2 release of the pipeline. We also report performance scores produced by the pipeline for different languages and language varieties. CLASSLA-Stanza exhibits consistently high performance across all the supported languages and outperforms its parent pipeline Stanza at all the supported tasks. We also present the pipeline’s new functionality that enables efficient processing of web data and describe the efficiency of the pipeline for annotating written transcripts of spoken data.

Source: Contributions to Contemporary History

DOI: 10.51663/pnz.65.3.05

Authors: Luka Terčon, Kaja Dobrovoljc, Nikola Ljubešić

Institutions: University of Ljubljana, Jožef Stefan Institute, Jožef Stefan International Postgraduate School, Institute of Contemporary History

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: European Commission, Javna Agencija za Raziskovalno Dejavnost RS, European Regional Development Fund, Innovation and Networks Executive Agency