Background: Text summarization is a challenging problem in Natural Language Processing, which involves condensing the content of textual documents without losing their overall meaning and information content, In the domain of bio-medical research, summaries are critical for efficient data analysis and information retrieval. While several bio-medical text summarizers exist in the literature, they often miss out on an essential text aspect: text semantics.
Results: This paper proposes a novel extractive summarizer that preserves text semantics by utilizing bio-semantic models. We evaluate our approach using ROUGE on a standard dataset and compare it with three state-of-the-art summarizers. Our results show that our approach outperforms existing summarizers.
Conclusion: The usage of semantics can improve summarizer performance and lead to better summaries. Our summarizer has the potential to aid in efficient data analysis and information retrieval in the field of biomedical research.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11022460 | PMC |
| http://dx.doi.org/10.1186/s12859-024-05712-x | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A continuous-action deep reinforcement learning-based agent for coronary artery centerline extraction in coronary CT angiography images.
Med Biol Eng Comput
January 2025
Faculty of Computing, Harbin Institute of Technology, Harbin, 150001, China.
The lumen centerline of the coronary artery allows vessel reconstruction used to detect stenoses and plaques. Discrete-action-based centerline extraction methods suffer from artifacts and plaques. This study aimed to develop a continuous-action-based method which performs more effectively in cases involving artifacts or plaques.
View Article and Find Full Text PDFData-Driven Accelerated Discovery Coupled with Precise Synthesis of Single-Atom Catalysts for Robust and Efficient Water Purification.
Angew Chem Int Ed Engl
January 2025
USTC: University of Science and Technology of China, Environmental Science and Engineering, CHINA.
The development of advanced catalysts frequently employs trial-and-error methods and is lack of highly controlled synthesis, resulting in unsatisfactory development efficiency and performance. Here we propose a data-driven prediction coupled with precise synthesis strategy to accelerate the development of single-atom catalysts (SACs) for efficient water purification. The data-driven approach enables the rapid screening and prediction of high-performance SACs from 43 metals-N4 structures comprising transition and main group metal elements, followed by validation and structural modulation for improved performance through a highly controllable hard-template method.
View Article and Find Full Text PDFDeep Learning for Staging Periodontitis Using Panoramic Radiographs.
Oral Dis
January 2025
Salivary Gland Disease Center and Beijing Key Laboratory of Tooth Regeneration and Function Reconstruction, Beijing Laboratory of Oral Health and Beijing Stomatological Hospital, Capital Medical University, Beijing, China.
Objectives: Utilizing a deep learning approach is an emerging trend to improve the efficiency of periodontitis diagnosis and classification. This study aimed to use an object detection model to automatically annotate the anatomic structure and subsequently classify the stages of radiographic bone loss (RBL).
Materials And Methods: In all, 558 panoramic radiographs were cropped to 7359 pieces of individual teeth.
Application of Syndromic Panels for respiratory Tract Infections in Lung Transplantation: A Critical Review on Current Evidence and Future Perspectives.
Transpl Infect Dis
January 2025
Infectious Diseases Unit, Foundation IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milan, Italy.
Background: Infections are a common complication among lung transplant recipients (LuTR), particularly in the first year post-transplant, with respiratory tract infections (RTI) being predominant. Syndromic molecular panels have been suggested to reduce morbidity and mortality by providing a diagnosis quickly. However, integrating these panels into clinical practice remains debated.
View Article and Find Full Text PDFPerceptions of eHealth and digitalization among professional anaesthesia personnel: A Swedish national study.
Acta Anaesthesiol Scand
March 2025
Care in High Technological Environments, Department of Health Sciences, Lund University, Lund, Sweden.
Background: The objective of this study was to evaluate anaesthesia care professionals' perceptions and attitudes regarding the implementation and advancement of digital solutions in perioperative care.
Methods: Anaesthesia personnel working in public Swedish institutions where anaesthesia is administered were invited to respond to an online survey regarding their attitudes towards digitalization in the workplace and their perceptions of information provision and future digitalization within anaesthesia and surgical healthcare. Data were analyzed using descriptive statistics, independent-samples Kruskal-Wallis tests, and post-hoc pairwise comparisons.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!