Feature extraction and evaluation for BioMedical Question Answering
This work addresses performance optimization in biomedical question answering pipelines, but it is incremental as it focuses on evaluating existing modules rather than introducing new methods.
The paper tackled the problem of biomedical question answering by evaluating feature extraction and sentence selection modules across four question types, resulting in defined metrics for future pipeline improvements.
In this paper, we present our work on the BioASQ pipeline. The goal is to answer four types of questions: summary, yes/no, factoids, and list. Our goal is to empirically evaluate different modules involved: the feature extractor and the sentence selection block. We used our pipeline to test the effectiveness of each module for all kinds of question types and perform error analysis. We defined metrics that are useful for future research related to the BioASQ pipeline critical to improve the performance of the training pipeline.