Top K Relevant Passage Retrieval for Biomedical Question Answering

TL;DR

This paper improves biomedical question answering by fine-tuning dense passage retrieval on PubMed articles, achieving higher accuracy than traditional methods and addressing the domain-specific challenges of medical information retrieval.

Contribution

It adapts and fine-tunes the Dense Passage Retrieval framework for biomedical questions using PubMed, enhancing retrieval accuracy in the medical domain.

Findings

Achieved 0.81 F1 score on BioASQ dataset.

Outperformed traditional sparse retrieval models.

Demonstrated effectiveness of domain-specific fine-tuning.

Abstract

Question answering is a task that answers factoid questions using a large collection of documents. It aims to provide precise answers in response to the user's questions in natural language. Question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. On the web, there is no single article that could provide all the possible answers available on the internet to the question of the problem asked by the user. The existing Dense Passage Retrieval model has been trained on Wikipedia dump from Dec. 20, 2018, as the source documents for answering questions. Question answering (QA) has made big strides with several open-domain and machine comprehension systems built using large-scale annotated datasets. However, in the clinical domain, this problem remains relatively unexplored. According to multiple surveys, Biomedical Questions cannot be answered correctly from Wikipedia Articles. In this work, we work on the existing DPR framework for the biomedical domain and retrieve answers from the Pubmed articles which is a reliable source to answer medical questions. When evaluated on a BioASQ QA dataset, our fine-tuned dense retriever results in a 0.81 F1 score.