vix.ing · top · new · best · stats · spec

End-to-End Retrieval with Learned Dense and Sparse Representations Using Lucene

2023/11/30 by Haonan Chen, Chen, Haonan, Carlos Lassance +3 · 1 citation
Computer Science · Materials Science · #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning in Materials Science #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2311.18503

openalex publication_date 2023/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The bi-encoder architecture provides a framework for understanding machine-learned retrieval models based on dense and sparse vector representations. Although these representations capture parametric realizations of the same underlying conceptual framework, their respective implementations of top-k similarity search require the coordination of different software components (e.g., inverted indexes, HNSW indexes, and toolkits for neural inference), often knitted together in complex architectures. In this work, we ask the following question: What's the simplest design, in terms of requiring the fewest changes to existing infrastructure, that can support end-to-end retrieval with modern dense and sparse representations? The answer appears to be that Lucene is sufficient, as we demonstrate in Anserini, a toolkit for reproducible information retrieval research. That is, effective retrieval with modern single-vector neural models can be efficiently performed directly in Java on the CPU. We examine the implications of this design for information retrieval researchers pushing the state of the art as well as for software engineers building production search systems.

Cited by

Related