DIP - Desafio de Identificação de Personagens: objectivo, organização, recursos e resultados

  • Diana Santos Linguateca / Universidade de Oslo
  • Cristina Mota INESC-ID & Linguateca
  • Emanoel Pires UEMA/UFPI
  • Marcia Langfeldt
  • Rebeca Schumacher Fuão
  • Roberto Willrich Universidade Federal de Santa Catarina
Keywords: evaluation contest, lusophone literature, character identification

Abstract

This paper presents in-depth DIP, the character identification challenge in Portuguese. It aims to fully document its motivation, the choices taken, the organization process, the evaluation contest proper, and the results achieved. It also presents the public resources created by DIP. We report on what we have learned with DIP's organization, and what we learned about lusophone literature. For example, in the works analysed by DIP (1) the number of feminine characters is way less than masculine characters, (2) every work has some character with more than a name, (3) the most frequent profession is priest, (4) the works refer more to fathers than to mothers, and (5) diminutives are pretty frequent as character names.

Published
2023-07-04
How to Cite
Santos, D., Mota, C., Pires, E., Langfeldt, M., Schumacher Fuão, R., & Willrich, R. (2023). DIP - Desafio de Identificação de Personagens: objectivo, organização, recursos e resultados. Linguamática, 15(1), 3-30. https://doi.org/10.21814/lm.15.1.399
Section
DIP - Character Identification Challenge