Abstract

PEMBERTY TAMAYO, José Luis; MOLINA MEJIA, Jorge Mauricio  and  VALLEJO ZAPATA, Víctor Julián. UnderRL Tagger: A Grammar Tagger for Technologically Under-Supported and Minority Languages. Forma. func. [online]. 2023, vol.36, n.2, e1984.  Epub June 08, 2023. ISSN 0120-338X.  https://doi.org/10.15446/fyf.v36n2.101984.

This paper presents UnderRL Tagger, a freely available software program designed for morphosyntactic tagging (POS tagging) in languages that do not have automatic taggers. The program aims to facilitate working with corpora in these technologically under-supported languages and in minority languages, thus contributing to revitalization processes based on descriptive research and computational tools. UnderRL Tagger allows the manual tagging process to gradually become automatic thanks to a system that allows remembering and reusing tags, handling large amounts of text and generating output files in XML format with tags based on the standardized EAGLES system. This article shows the process of modeling and development of the system, its different functionalities and the prospects for further work.

Keywords : morphosyntactic tagging; technologically under-supported languages; minority languages; text corpora; natural language processing.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )