paper-with-me

홈 › Papers

Hybrid Retrieval for COVID-19 Literature: Comparing Rank Fusion and Projection Fusion with Diversity Reranking

2026-04-15 · Harishkumar Kishorkumar Prajapati arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.13728

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Pandemic Literature Search: Finding Information on COVID-19

2020-12-01 · ALTA 2020 12 · Vincent Nguyen, Maciek Rybinski, Sarvnaz Karimi, Zhenchang Xing

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 RetrievalRetrieval

Searching Scientific Literature for Answers on COVID-19 Questions

2020-07-06 · Vincent Nguyen, Maciek Rybinski, Sarvnaz Karimi, Zhenchang Xing

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…

Retrieval

COV19IR : COVID-19 Domain Literature Information Retrieval

2022-11-08 · Arusarka Bose, Zili Zhou, Guandong Xu

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 AnsweringRetrieval

CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search

2020-11-03 · Chenyan Xiong, Zhenghao Liu, Si Sun, Zhuyun Dai 외

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 RetrievalRetrieval

Frugal neural reranking: evaluation on the Covid-19 literature

2020-12-01 · EMNLP (NLP-COVID19) 2020 12 · Tiago Almeida, Sérgio Matos

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