Mengfei Lan's Preliminary Exam

Biomedical literature plays a crucial role for scientific knowledge acquisition. However, the vast volume of biomedical literature presents significant challenges in efficiently locating and extracting the needed information. Biomedical natural language processing (BioNLP) techniques, which facilitate quick processing of large-scale biomedical texts, becomes increasingly important to address this challenge. Most existing BioNLP works focus on extracting biomedical knowledge in the form of named entities or entity relationships from literature, but overlooking the argument roles—such as hypothesis and novel findings—played by the entities and their relationships in the paper. These argument roles could influence the extracted knowledge reliability (e.g. hypothesis) and interpretability. Therefore, biomedical argument mining, as the process of automatic identification and analysis of arguments within biomedical literature, should receive more attention to advance knowledge interpretation and extraction. Recent advancements in large language models (LLMs) have opened new opportunities for biomedical argument mining with their strong abilities in understanding complex semantic dependencies from text. This thesis explores how to leverage LLMs to advance biomedical argument mining. Three specific challenges in the field are analyzed: extracting rhetorical roles for sentences in biomedical abstracts, contextualizing claims through understanding of study limitations, and claim extraction within a rich context.

Question? Contact Mengfei Lan.