Probability model with Ensemble learning and Data augmentation for named entity recognition (NER) and relation extraction (RE) tasks

Abstract

Biomedical Natural Language Processing (NLP) is an innovative field that uses advanced computational techniques to extract and utilize information from biomedical literature. It enables researchers and healthcare professionals to access, analyze, and apply textual data for various purposes, including clinical decision support, drug discovery, and knowledge discovery. In this paper, we introduce a multi-techniques approach to biomedical relation extraction and named entity recognition, demonstrating competitive performance when evaluated using Precision, Recall, and F1 Score in comparison to existing methods.

This article is part of the Proceedings of the BioCreative VIII Challenge and Workshop: Curation and Evaluation in the era of Generative Models.