Hybrid Retrieval for COVID-19 Literature: Comparing Rank Fusion and Projection Fusion with Diversity Reranking
We present a hybrid retrieval system for COVID-19 scientific literature, evaluated on the TREC-COVID benchmark (171,332 papers, 50 expert queries). The system implements six retrieval configurations spanning sparse (SPLADE), dense (BGE), rank-level fusion (RRF), and a projection-based vector fusion (B5) approach. RRF fusion achieves the best relevance (nDCG@10 = 0.828), outperforming dense-only by 6.1% and sparse-only by 14.9%. Our projection fusion variant reaches nDCG@10 = 0.678 on expert queries while being 33% faster (847 ms vs. 1271 ms) and producing 2.2x higher ILD@10 than RRF. Evaluation across 400 queries -- including expert, machine-generated, and three paraphrase styles -- shows that B5 delivers the largest relative gain on keyword-heavy reformulations (+8.8%), although RRF remains best in absolute nDCG@10. On expert queries, MMR reranking increases intra-list diversity by 23.8-24.5% at a 20.4-25.4% nDCG@10 cost. Both fusion pipelines evaluated for latency remain below the sub-2 s target across all query sets. The system is deployed as a Streamlit web application backed by Pinecone serverless indices.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Pandemic Literature Search: Finding Information on COVID-19
Finding information related to a pandemic of a novel disease raises new challenges for information seeking and retrieval, as the new information becomes available gradually. We investigate how to better rank information …
Information RetrievalRetrievalSearching Scientific Literature for Answers on COVID-19 Questions
Finding answers related to a pandemic of a novel disease raises new challenges for information seeking and retrieval, as the new information becomes available gradually. TREC COVID search track aims to assist in creating…
RetrievalCOV19IR : COVID-19 Domain Literature Information Retrieval
Increasing number of COVID-19 research literatures cause new challenges in effective literature screening and COVID-19 domain knowledge aware Information Retrieval. To tackle the challenges, we demonstrate two tasks alon…
Information RetrievalQuestion AnsweringRetrievalCMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search
Neural rankers based on deep pretrained language models (LMs) have been shown to improve many information retrieval benchmarks. However, these methods are affected by their the correlation between pretraining domain and …
Domain AdaptationFew-Shot LearningInformation RetrievalRetrievalFrugal neural reranking: evaluation on the Covid-19 literature
The Covid-19 pandemic urged the scientific community to join efforts at an unprecedented scale, leading to faster than ever dissemination of data and results, which in turn motivated more research works. This paper prese…
Information RetrievalRerankingRetrieval