Year: 2024
Type: conference-paper
Abstract: Identifying participants in narratives is important to understand and extract meaning from unstructured texts. This paper investigates the use of DBpedia and Wikifier for this task. We tested these two knowledge base platforms to evaluate their performance in recognizing and extracting entities in Portuguese-language journalistic narrative texts. The results show that both DBpedia and Wikifier present similar results in identifying participants, around 0.40 in the f1-score. The objective of this paper is to study the potential of knowledge bases to improve the understanding of narratives, in addition to suggesting directions for future research in this domain.
Authors: Juliana Machado, Evelin Amorim
Institutions: Universidade Federal de Santa Catarina, INESC TEC
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4403816400