Course Description

Even though text mining has been widely studied, there still exist many challenges in biomedical text mining today. The literature has shown that conventional text mining techniques and data mining algorithms do not fit biomedical corpora since many domain-specified issues are involved. Therefore, the area of BioNLP has received considerable attention from researchers with different knowledge backgrounds. It is a combination of computational linguistics, bioinformatics as well as medical informatics. Consequently, biological scientists and the biomedical researcher, clinicians, and the general public would be interested in the research results in BioNLP.

This course introduces BioNLP, including the objectives, tasks, methodologies, and valuable tools. It also contains some computational biology projects employing text mining. The seminar part comprises a collection of NLP procedures and tasks for participants to practice. The hands-on exercises can help enhance the content in the lecture.


  1. Give an overview of BioNLP. Elaborate the tasks in BioNLP along with the previous and SOTA methods.
  2. Introduce the benchmark datasets for BioNLP and some of the deep learning approaches.
  3. Demonstrate the application of text mining on the knowledge databases for computational biology.