Data-Centric and Model-Centric Approaches for Biomedical Question Answering

Wonjin Yoon, Jaehyo Yoo, Sumin Seo, Mujeen Sung, Minbyul Jeong, Gangwoo Kim, Jaewoo Kang

Abstract: Biomedical question answering (BioQA) is the process of automated information extraction from the biomedical literature, and as the number of accessible biomedical papers is increasing rapidly, BioQA is attracting more attention. In order to improve the performance of BioQA systems, we designed strategies for the sub-tasks of BioQA and assessed their effectiveness using the BioASQ dataset. We designed data-centric and model-centric strategies based on the potential for improvement for each sub-task. For example, model design for the factoid-type questions has been explored intensely but the potential of increased label consistency has not been investigated (data-centric approach). On the other hand, for list-type questions, we apply the sequence tagging model as it is more natural for the multi-answer (i.e. multi-label) task (model-centric approach).