The objective of the proposed research is to advance the performance, robustness, and practical applicability of Natural language processing (NLP) tools for information retrieval and clinical data structuring to support effective knowledge extraction. Biomedical records contain a vast quantity of unstructured data, which can offer valuable insights into patient care and clinical research. NLP has been increasingly used to automate clinical information extraction from biomedical text, but existing systems still face limitations, restricting their reliable use in real-world settings. This thesis develops methods to: (1) structure clinical data to facilitate knowledge discovery, (2) improve the reliability of biomedical search by surfacing the most accurate matches, and (3) expand retrieval coverage to identify a broader set of relevant results in biomedical databases.