Improving Biomedical Information Retrieval with Neural Retrievers

TL;DR

This paper enhances biomedical information retrieval by developing neural retrievers trained with synthetic data, novel pre-training tasks, and a multi-vector encoding model, outperforming traditional methods especially in small-corpus scenarios.

Contribution

It introduces a template-based question generation method, two new pre-training tasks, and the Poly-DPR model for improved neural retrieval in biomedical domains.

Findings

Poly-DPR outperforms existing neural approaches.

Our method beats BM25 in small-corpus settings.

Hybrid models further improve retrieval in large-corpus scenarios.

Abstract

Information retrieval (IR) is essential in search engines and dialogue systems as well as natural language processing tasks such as open-domain question answering. IR serve an important function in the biomedical domain, where content and sources of scientific knowledge may evolve rapidly. Although neural retrievers have surpassed traditional IR approaches such as TF-IDF and BM25 in standard open-domain question answering tasks, they are still found lacking in the biomedical domain. In this paper, we seek to improve information retrieval (IR) using neural retrievers (NR) in the biomedical domain, and achieve this goal using a three-pronged approach. First, to tackle the relative lack of data in the biomedical domain, we propose a template-based question generation method that can be leveraged to train neural retriever models. Second, we develop two novel pre-training tasks that are closely aligned to the downstream task of information retrieval. Third, we introduce the ``Poly-DPR'' model which encodes each context into multiple context vectors. Extensive experiments and analysis on the BioASQ challenge suggest that our proposed method leads to large gains over existing neural approaches and beats BM25 in the small-corpus setting. We show that BM25 and our method can complement each other, and a simple hybrid model leads to further gains in the large corpus setting.