Advances in Biomedical Entity and Relation Extraction: Techniques and Applications

Entity and entity relation extraction is an important task in biomedical language processing. It helps in extracting relevant and meaningful information from unstructured text and provides a way to structure the information. Further useful information from entities and semantic relations between them can be helpful in analyzing, processing and visualizing the textual data. Entity extraction is mostly the first step in data pre-processing for many tasks such as question answering, information retrieval, and information extraction tasks. In addition, it is also useful in almost all biomedical text mining activities, including classification and clustering to discover the new and the existing knowledge hidden in unstructured text. Entity extraction is a complicated task in biomedical domain due to multiple challenges such as complex terminology, ambiguities, lack of labelled data, etc. Moreover rich relations exist between biomedical entities that make relation extraction task quite challenging. A lot of efforts have been done to develop approaches and tools for extracting entities and relation between these entities. The chapter provides an overview of concepts in biomedical entity extraction with a lot of examples. It also presents the important tools for extracting entities and their relations along with Python code for accessing these tools.