Active Learning for Assisted Corpus Construction: A Case Study in Knowledge Discovery from Biomedical Text

no code implementations • RANLP 2021 • Hian Cañizares-Díaz, Alejandro Piad-Morffis, Suilan Estevez-Velarde, Yoan Gutiérrez, Yudivián Almeida Cruz, Andres Montoyo, Rafael Muñoz-Guillena

Experimental results suggest that the query strategy reduces by between 35% and 40% the number of sentences that must be manually annotated to develop systems able to reach a target F1 score, while the pre-annotation strategy produces an additional 24% reduction in the total annotation time.

Active Learning Sentence +1

Demo Application for the AutoGOAL Framework

no code implementations • COLING 2020 • Suilan Estevez-Velarde, Alejandro Piad-Morffis, Yoan Guti{\'e}rrez, Andres Montoyo, Rafael Mu{\~n}oz-Guillena, Yudivi{\'a}n Almeida Cruz

This paper introduces a web demo that showcases the main characteristics of the AutoGOAL framework.

AutoML BIG-bench Machine Learning

Automatic Discovery of Heterogeneous Machine Learning Pipelines: An Application to Natural Language Processing

no code implementations • COLING 2020 • Suilan Estevez-Velarde, Yoan Guti{\'e}rrez, Andres Montoyo, Yudivi{\'a}n Almeida Cruz

The system is freely available and includes in-built compatibility with a large number of popular machine learning frameworks, which makes our approach useful for solving practical problems with relative ease and effort.

AutoML BIG-bench Machine Learning