VSE knjižnice (vzajemna bibliografsko-kataložna baza podatkov COBIB.SI)
  • CLASSLA-Stanza : the next step for linguistic processing of South Slavic languages
    Terčon, Luka ; Ljubešić, Nikola, 1979-
    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
    Vir: ArXiv.org [Elektronski vir]. - ISSN 2331-8422 (eprint 2308.04255, [in press] 2023)
    Vrsta gradiva - e-članek
    Leto - 2023
    Jezik - angleški
    COBISS.SI-ID - 187571459

    Povezava(-e):

    https://arxiv.org/abs/2308.04255
    DOI

Vnos na polico