Prompt-based Zero-shot Learning and Siamese Neural Network-based Few-shot Learning for Clinical Natural Language Processing


April 5th at  1:25 pm EST

Register – Free

Rapid growth in adoption of electronic health records (EHRs) has led to an unprecedented expansion in the availability of large longitudinal datasets. Clinical natural language processing (NLP) technologies have played a crucial role as much of detailed patient information in EHRs is embedded in narrative clinical documents. Clinical NLP systems leverage techniques ranging from rule-based algorithms to advanced deep learning neural networks. Recent advancement in large language models (LLMs) has brought new excitement to the NLP field, particularly due to the success launch of ChatGPT. These LLMs are fundamentally changing the way we are doing for biomedical and clinical NLP tasks, providing a new paradigm to these tasks with zero/few-shot learning approaches. This talk will walk through the new promise brought by LLMs with recent research for clinical NLP.

About the speaker

Yanshan Wang

Vice Chair of Research and Assistant Professor at University of Pittsburgh

Yanshan Wang is a Vice Chair of Research and Assistant Professor at the University of Pittsburgh. His research interests focus on artificial intelligence (AI), natural language processing (NLP), machine learning, and deep learning methodologies and applications in healthcare. His research goal is to leverage different dimensions of data and data-driven computational approaches to meet the needs of clinicians, researchers, and patients.



Online Event: April 4-5, 2023



Presented by