paper-with-me

Papers

Searching Dense Representations with Inverted Indexes

2023-12-04 · Jimmy Lin, Tommaso Teofili

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".

📄 PDF Abstract BibTeX arXiv:2312.01556

Code (0)

등록된 구현이 없습니다.

Tasks

Passage RankingRetrieval

Similar Papers 제목 키워드 기반

Anserini Gets Dense Retrieval: Integration of Lucene's HNSW Indexes

2023-04-24 · Xueguang Ma, Tommaso Teofili, Jimmy Lin

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 RetrievalRetrieval

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

2023-11-30 · Haonan Chen, Carlos Lassance, Jimmy Lin

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 RetrievalRetrieval

Operational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes?

2024-09-10 · Jimmy Lin

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…

Retrieval

An Efficient Indexing and Searching Technique for Information Retrieval for Urdu Language

2021-02-28 · Muhammad Mudassar Qureshi, Muhammad Shoaib, Kalsoom

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 RetrievalRetrieval

Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines

2017-08-01 · WS 2017 8 · Jan Rygl, Jan Pomik{\'a}lek, Radim {\v{R}}eh{\r{u}}{\v{r}}ek, Michal R{\r{u}}{\v{z}}i{\v{c}}ka 외

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