• Exploiting Cross-Dialectal Gold Syntax for Low-Resource Historical Languages: Towards a Generic Parser for Pre-Modern Slavic

    Author(s):
    Nilo Pedrazzini (see profile)
    Date:
    2020
    Item Type:
    Conference proceeding
    Conf. Title:
    CHR 2020: Workshop on Computational Humanities Research
    Conf. Loc.:
    Amsterdam, The Netherlands
    Conf. Date:
    November 18–20, 2020
    Tag(s):
    low-resource languages, dependency parsing, neural networks, Early Slavic
    Permanent URL:
    http://dx.doi.org/10.17613/5t12-hk29
    Abstract:
    This paper explores the possibility of improving the performance of specialized parsers for pre- modern Slavic by training them on data from different related varieties. Because of their linguistic heterogeneity, pre-modern Slavic varieties are treated as low-resource historical languages, whereby cross-dialectal treebank data may be exploited to overcome data scarcity and attempt the training of a variety-agnostic parser. Previous experiments on early Slavic dependency parsing are discussed, particularly with regard to their ability to tackle different orthographic, regional and stylistic features. A generic pre-modern Slavic parser and two specialized parsers – one for East Slavic and one for South Slavic – are trained using jPTDP [8], a neural network model for joint part-of-speech (POS) tagging and dependency parsing which had shown promising results on a number of Universal Dependency (UD) treebanks, including Old Church Slavonic (OCS). With these experiments, a new state of the art is obtained for both OCS (83.79% unlabelled attachment score (UAS) and 78.43% labelled attachment score (LAS)) and Old East Slavic (OES) (85.7% UAS and 80.16% LAS).
    Metadata:
    Published as:
    Conference proceeding    
    Status:
    Published
    Last Updated:
    1 week ago
    License:
    All Rights Reserved
    Share this:

    Downloads

    Item Name:pdf pedrazzini-2020.pdf
     Download View in browser
    Activity: Downloads: 5