Searching Dense Representations with Inverted Indexes
Nearly all implementations of top-$k$ retrieval with dense vector representations today take advantage of hierarchical navigable small-world network (HNSW) indexes. However, the generation of vector representations and efficiently searching large collections of vectors are distinct challenges that can be decoupled. In this work, we explore the contrarian approach of performing top-$k$ retrieval on dense vector representations using inverted indexes. We present experiments on the MS MARCO passage ranking dataset, evaluating three dimensions of interest: output quality, speed, and index size. Results show that searching dense representations using inverted indexes is possible. Our approach exhibits reasonable effectiveness with compact indexes, but is impractically slow. Thus, while workable, our solution does not provide a compelling tradeoff and is perhaps best characterized today as a "technical curiosity".
Code (0)
등록된 구현이 없습니다.
Tasks
Passage RankingRetrievalSimilar Papers 제목 키워드 기반
Anserini Gets Dense Retrieval: Integration of Lucene's HNSW Indexes
Anserini is a Lucene-based toolkit for reproducible information retrieval research in Java that has been gaining traction in the community. It provides retrieval capabilities for both "traditional" bag-of-words retrieval…
Information RetrievalRetrievalEnd-to-End Retrieval with Learned Dense and Sparse Representations Using Lucene
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 …
CPUInformation RetrievalRetrievalOperational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes?
Practitioners working on dense retrieval today face a bewildering number of choices. Beyond selecting the embedding model, another consequential choice is the actual implementation of nearest-neighbor vector search. Whil…
RetrievalAn Efficient Indexing and Searching Technique for Information Retrieval for Urdu Language
Indexing techniques are used to improve retrieval of data in response to certain search condition. Inverted files are mostly used for creating indexes. This paper proposes indexing technique for Urdu language. Language p…
Information RetrievalRetrievalSemantic Vector Encoding and Similarity Search Using Fulltext Search Engines
Vector representations and vector space modeling (VSM) play a central role in modern machine learning. We propose a novel approach to {`}vector similarity searching{'} over dense semantic representations of words and doc…
Information RetrievalRepresentation Learning