Mejoras aplicadas a la extracción de relaciones semánticas para la Web en español

This paper introduces a novel method of Open Information Extraction in Spanish called ECMes. This method is compared to other similar methods in the state-of-the-art using two different testing datasets: one is a well known dataset, already used in previous related works and the second dataset was c...

Full description

Saved in:
Bibliographic Details
Published in:Procesamiento del Lenguaje Natural 2021-03, Vol.66, p.133
Main Authors: Rodríguez, Juan M, Merlino, Hernán D, Pesado, Patricia
Format: Article
Language:Spanish
Subjects:
Datasets
Information retrieval
Natural language processing
Recall
Semantic analysis
Spanish language
Webs
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper introduces a novel method of Open Information Extraction in Spanish called ECMes. This method is compared to other similar methods in the state-of-the-art using two different testing datasets: one is a well known dataset, already used in previous related works and the second dataset was constructed specifically for this article using heterogeneous data sources. In the first dataset ECMes obtained the highest precision, recall and F1 measurement. In the second dataset, ECMes obtained the highest recall and the highest F1 measurement.
ISSN:1135-5948
1989-7553
DOI:10.26342/2021-66-11