Thesis Format
Monograph
Degree
Master of Science
Program
Computer Science
Collaborative Specialization
Artificial Intelligence
Supervisor
Mercer Robert E
Abstract
The proliferation of biomedical research literature has led to an urgent need for efficient methods to navigate and extract relevant claims from the extensive corpus of research articles. Manually identifying argumentative claims within these articles can be labor-intensive and time-consuming. This research addresses the complexities associated with claim detection in biomedical literature by proposing a novel approach that harnesses pre-trained models and employs titles as potential indicators for identifying argumentative claims across various sections of research articles. A notable contribution of this research is the formulation of a balanced subset from the MeSHup dataset, specifically targeting articles that contain verbs in their titles. Additionally, this study introduces an alternative methodology that involves fine-tuning biomedical language models to enhance the precision of claim detection in the text of research articles. The efficacy of these methodologies was rigorously assessed through the use of manual annotations conducted by trained annotators. As part of this research, we also develop a new dataset for biomedical argumentative claim detection using MeSHup articles. Ultimately, the results of this thesis will help to streamline literature reviews, facilitating the extraction of critical insights from scientific texts with heightened accuracy and efficiency, thereby advancing the understanding and application of biomedical research.
Summary for Lay Audience
The rapid increase in biomedical research papers has created a need for better ways to find important claims within this vast amount of literature. Manually searching through these articles can be tedious and time-consuming. This thesis addresses the challenges of claim detection by introducing a new approach that uses advanced models and analyzes titles to identify claims in different sections of research papers. A key part of this work is the creation of a specialized dataset focused on articles with titles containing tense verbs. Additionally, the study fine-tunes a biomedical language model to improve the accuracy of identifying claims within the text of the articles. The effectiveness of these methods was tested through careful manual review of claims. Overall, this research aims to make review of biomedical literature more efficient, helping researchers quickly extract valuable insights from scientific texts and improving the understanding of biomedical research.
Recommended Citation
Patil, Gaurav N., "IDENTIFYING ARGUMENTATIVE CLAIMS IN BIOMEDICAL RESEARCH ARTICLES" (2025). Electronic Thesis and Dissertation Repository. 10691.
https://ir.lib.uwo.ca/etd/10691
