| Knowledge about genes and gene products continues to grow exponentially in electronic textual databases. Due to the complexity and homogeneity of the biomedical domain, synthesis of all of the available information about thousands of genes and proteins is a prohibitive task. Text mining can simplify this scenario by aiding researchers in finding relevant facts in vast biomedical textual databases. This thesis explores how natural language processing (NLP) and machine learning methods can be used to represent, filter, extract and infer genetic knowledge in biomedical text. |
