MSQ-BioBERT: Ambiguity Resolution to Enhance BioBERT Medical Question-Answering

Muzhe Guo, Muhao Guo, Edward T. Dougherty, Fang Jin

Keywords: Question answering, Question augmentation, BioBERT, Matrix approximation

TL;DR: A way to improve BioBERT Question-answering using multiple synonymous questions.

Abstract: Bidirectional Encoder Representations from Transformers (BERT) and its biomedical variation (BioBERT) achieve impressive results on the SQuAD or medical question-answering (QA) datasets, and so they are widely used for a variety of passage-based QA tasks. However, their performances rapidly deteriorate when encountering passage and context ambiguities. This issue is prevalent and unavoidable in many fields, notably the medical field. To address this issue, we introduce a novel approach called the Multiple Synonymous Questions BioBERT (MSQ-BioBERT), which integrates question augmentation, rather than the typical single question used by traditional BioBERT, to elevate performance. Experiments with both an ambiguous medical dataset and open biomedical datasets demonstrate the significant performance gains of the MSQ-BioBERT approach, showcasing a new method for addressing ambiguity in QA tasks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)