CorefLat. Annotazione e modellizzazione per la risoluzione di coreferenze in latino

Eleonora Delfino (Dipartimento di Lingue e Letterature, Comunicazione, Formazione e Società, Università degli Studi di Udine), Roberta Grazia Leotta (Dipartimento di Scienze Linguistiche e Letterature Straniere, Università Cattolica del Sacro Cuore di Milano), Marco Passarotti (Dipartimento di Scienze Linguistiche e Letterature Straniere, Università Cattolica del Sacro Cuore di Milano), Francesco Mambrini (Dipartimento di Scienze Linguistiche e Letterature Straniere, Università Cattolica del Sacro Cuore di Milano)

Abstract

This study is part of a broader research project on coreference phenomena in the Latin language, entitled CorefLat. This paper focuses specifically on the publication as Linked Open Data of a set of coreference annotations performed on a selection of Latin texts. The annotations are applied to texts already available as Linked Open Data within the LiLa Knowledge Base, a collection of interoperable linguistic resources for Latin. CorefLat systematically identifies and tags entities and mentions, establishing relational links between them. The annotated corpus covers various historical periods and literary genres, including Augustine’s Confessiones, Plautus’ Curculio, Caesar’s De Bello Gallico, and Seneca’s Medea, offering a balanced dataset suitable for broad linguistic analysis. In this paper we also provide quantitative data on the annotations carried out so far, by showing some patterns and distributions of the linguistic phenomena within the dataset. Building on this, the paper describes how coreference phenomena are encoded as Linked Open Data using standard classes and object properties from the POWLA framework.

DOI: 10.4424/lam142025-3

Keywords

Latin Language; Computational Linguistics; Syntax; Coreference.

Views: 10

Download PDF

Downloads: 9