Need help making sense of complex biomedical research papers? This paper introduces a novel extractive summarizer that preserves text semantics by utilizing bio-semantic models. It aims to address the challenge of condensing textual documents while retaining their overall meaning and information content, a crucial task for efficient data analysis and information retrieval in the biomedical field. The summarizer utilizes bio-semantic models to extract essential information while preserving the underlying meaning of the text. The approach is evaluated using ROUGE on a standard dataset and compared with three state-of-the-art summarizers to access performance. Results show that the proposed approach outperforms existing summarizers, demonstrating the potential of semantics to improve summarizer performance and lead to better summaries. This summarizer has the potential to aid in efficient data analysis and information retrieval in the field of biomedical research.
Published in BMC Bioinformatics, this article is aligned with the journal's focus on bioinformatics and computational biology. It addresses the challenge of text summarization in the biomedical domain, a key area of interest for bioinformatics researchers. By presenting a novel summarizer that utilizes bio-semantic models, the study contributes to the development of tools for efficient data analysis and information retrieval in biomedical research.