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

Luka Terčon, Nikola Ljubešić
8/8/2023
cs.CL

No official code found. Best implementation: clarinsi/classla (53 stars, last commit 2025-05-06).

Abstract

We present CLASSLA-Stanza, a pipeline for automatic linguistic annotation of the 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 2.1 release of the pipeline. We also report performance scores produced by the pipeline for different languages and varieties. CLASSLA-Stanza exhibits consistently high performance across all the supported languages and outperforms or expands its parent pipeline Stanza at all the supported tasks. We also present the pipeline's new functionality enabling efficient processing of web data and the reasons that led to its implementation.

View on arXivView PDF

Code Implementations(1)

clarinsi/classlaCommunity100%

CLASSLA Fork of the Official Stanford NLP Python Library for Many Human Languages

5322CSS, HTMLOct 3, 20191 years agoNOASSERTION

Similar Papers

LatinCy: Synthetic Trained Pipelines for Latin NLP

85% match2023

A Survey of Resources and Methods for Natural Language Processing of Serbian Language

84% match2023

HugNLP: A Unified and Comprehensive Library for Natural Language Processing

84% match1 repo2402023

PyThaiNLP: Thai Natural Language Processing in Python

84% match1 repo1.1k2023

Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language

83% match2023

O-Dang! The Ontology of Dangerous Speech Messages

83% match2022

Cite this paper

@article{teron2023classlastanza,
  title  = {CLASSLA-Stanza: The Next Step for Linguistic Processing of South Slavic Languages},
  author = {Luka Terčon and Nikola Ljubešić},
  year   = {2023},
  eprint = {2308.04255},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.04255v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.04255.svg)](https://codeofpaper.com/paper/2308.04255)

Discussion