Sequence tagging for biomedical extractive question answering

TL;DR

This paper introduces a sequence tagging method for biomedical extractive question answering that effectively handles questions requiring multiple answer spans, outperforming existing models without extra post-processing.

Contribution

The authors propose a novel multi-span extraction approach for biomedical QA, addressing the limitations of single-span models by directly predicting multiple answer spans.

Findings

Outperforms existing models on BioASQ datasets

Handles variable number of answer spans effectively

Eliminates need for post-processing steps

Abstract

Current studies in extractive question answering (EQA) have modeled the single-span extraction setting, where a single answer span is a label to predict for a given question-passage pair. This setting is natural for general domain EQA as the majority of the questions in the general domain can be answered with a single span. Following general domain EQA models, current biomedical EQA (BioEQA) models utilize the single-span extraction setting with post-processing steps. In this article, we investigate the question distribution across the general and biomedical domains and discover biomedical questions are more likely to require list-type answers (multiple answers) than factoid-type answers (single answer). This necessitates the models capable of producing multiple answers for a question. Based on this preliminary study, we propose a sequence tagging approach for BioEQA, which is a multi-span extraction setting. Our approach directly tackles questions with a variable number of phrases as their answer and can learn to decide the number of answers for a question from training data. Our experimental results on the BioASQ 7b and 8b list-type questions outperformed the best-performing existing models without requiring post-processing steps. Source codes and resources are freely available for download at https://github.com/dmis-lab/SeqTagQA