Avaliação no Desafio de Identificação de Personagens
Abstract
The first edition of the Character Identification Challenge (DIP) was a joint evaluation of computational solutions for the identification of characters in literary texts, as well as the extraction of characteristics and relationships of these characters. For this evaluation, it was necessary to define an evaluation methodology, including the selection of appropriate metrics for the problem of identifying characters in literary texts. This article surveys the evaluation methods employed in character identification in literary works and presents the concrete choices done in DIP. These choices resulted in the definition of the DIP evaluation methodology. The use of the proposed evaluation methodology is illustrated by the evaluation of the candidate solution submitted to DIP. We end the paper with some critical remarks and suggestions for improvement.
Copyright (c) 2023 Roberto Willrich, Diana Santos
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).