Math Graduate Student Seminar: Yuhang Jiang, Computer Science, UK

Open to Juniors, Seniors, and Grad Students

Refreshments will be provided.

Title: End-to-end Relation Extraction in Biomedical Domain

Abstract: The exponential growth of unstructured text data in the digital world, stemming from online platforms, social media, and digital documentation, presents both a challenge and an opportunity for knowledge extraction. Natural language processing (NLP) advancements have enabled the development of sophisticated technologies capable of understanding and leveraging this vast amount of unstructured data. We focus on Relation Extraction (RE), a key component of information extraction, which simplifies natural language into structured formats like (subject, object, predicate) triples, thereby facilitating tasks like database population and knowledge graph construction. In the biomedical domain, the challenges of relation extraction are magnified due to the highly specialized and technical nature of the language used, as well as the complexity of the concepts involved. Biomedical texts often contain dense scientific terminology, domain-specific jargon, and intricate relationships between biological entities, making the extraction process far more nuanced and intricate.