English
Related papers

Related papers: The Curse of Dense Low-Dimensional Information Ret…

200 papers

In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven to…

Information Retrieval · Computer Science 2021-07-14 Thibault Formal , Benjamin Piwowarski , Stéphane Clinchant

Relational queries, and in particular join queries, often generate large output results when executed over a huge dataset. In such cases, it is often infeasible to store the whole materialized output if we plan to reuse it further down a…

Databases · Computer Science 2018-03-28 Shaleen Deep , Paraschos Koutris

The field of compressed sensing has shown that a sparse but otherwise arbitrary vector can be recovered exactly from a small number of randomly constructed linear projections (or samples). The question addressed in this paper is whether an…

Information Theory · Computer Science 2010-01-26 Galen Reeves , Michael Gastpar

Sampling proper negatives from a large document pool is vital to effectively train a dense retrieval model. However, existing negative sampling strategies suffer from the uninformative or false negative problem. In this work, we empirically…

Computation and Language · Computer Science 2022-10-25 Kun Zhou , Yeyun Gong , Xiao Liu , Wayne Xin Zhao , Yelong Shen , Anlei Dong , Jingwen Lu , Rangan Majumder , Ji-Rong Wen , Nan Duan , Weizhu Chen

Efficiently retrieving a concise set of candidates from a large document corpus remains a pivotal challenge in Information Retrieval (IR). Neural retrieval models, particularly dense retrieval models built with transformers and pretrained…

Information Retrieval · Computer Science 2025-01-01 Haitian Chen , Qingyao Ai , Xiao Wang , Yiqun Liu , Fen Lin , Qin Liu

Although transformer-based models have shown strong performance in word- and sentence-level tasks, effectively representing long documents, especially in fields like law and medicine, remains difficult. Sparse attention mechanisms can…

Computation and Language · Computer Science 2026-01-01 Waheed Ahmed Abro , Zied Bouraoui

Dense retrievers have achieved state-of-the-art performance in various information retrieval tasks, but their robustness against tokenizer poisoning remains underexplored. In this work, we assess the vulnerability of dense retrieval systems…

Computation and Language · Computer Science 2024-10-29 Ming Zhong , Zhizhi Wu , Nanako Honda

This paper proposes a dual skipping guidance scheme with hybrid scoring to accelerate document retrieval that uses learned sparse representations while still delivering a good relevance. This scheme uses both lexical BM25 and learned neural…

Information Retrieval · Computer Science 2022-04-26 Yifan Qiao , Yingrui Yang , Haixin Lin , Tianbo Xiong , Xiyue Wang , Tao Yang

Matrices and more generally multidimensional arrays, form the backbone of computational studies. In this paper we demonstrate increases in computational efficiency by performing partial-tracing/tensor-contractions on sparse-arrays. It was…

Data Structures and Algorithms · Computer Science 2023-03-21 Julio Candanedo

Recently, Dense Retrieval (DR) has become a promising solution to document retrieval, where document representations are used to perform effective and efficient semantic search. However, DR remains challenging on long documents, due to the…

Information Retrieval · Computer Science 2022-11-22 Junying Chen , Qingcai Chen , Dongfang Li , Yutao Huang

Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain…

Computation and Language · Computer Science 2022-11-15 Xilun Chen , Kushal Lakhotia , Barlas Oğuz , Anchit Gupta , Patrick Lewis , Stan Peshterliev , Yashar Mehdad , Sonal Gupta , Wen-tau Yih

This paper is concerned with the problem of low rank plus sparse matrix decomposition for big data. Conventional algorithms for matrix decomposition use the entire data to extract the low-rank and sparse components, and are based on…

Numerical Analysis · Computer Science 2017-03-17 Mostafa Rahmani , George Atia

Neural sentence embedding models for dense retrieval typically rely on binary relevance labels, treating query-document pairs as either relevant or irrelevant. However, real-world relevance often exists on a continuum, and recent advances…

Information Retrieval · Computer Science 2025-08-12 Christos Tsirigotis , Vaibhav Adlakha , Joao Monteiro , Aaron Courville , Perouz Taslakian

Scaling up neural models has yielded significant advancements in a wide array of tasks, particularly in language generation. Previous studies have found that the performance of neural models frequently adheres to predictable scaling laws,…

Information Retrieval · Computer Science 2024-07-16 Yan Fang , Jingtao Zhan , Qingyao Ai , Jiaxin Mao , Weihang Su , Jia Chen , Yiqun Liu

A number of learned sparse and dense retrieval approaches have recently been proposed and proven effective in tasks such as passage retrieval and document retrieval. In this paper we analyze with a replicability study if the lessons learned…

Information Retrieval · Computer Science 2023-01-16 Gustavo Penha , Claudia Hauff

Inverted file structure is a common technique for accelerating dense retrieval. It clusters documents based on their embeddings; during searching, it probes nearby clusters w.r.t. an input query and only evaluates documents within them by…

Information Retrieval · Computer Science 2023-10-18 Peitian Zhang , Zheng Liu , Shitao Xiao , Zhicheng Dou , Jing Yao

The data structure at the core of large-scale search engines is the inverted index, which is essentially a collection of sorted integer sequences called inverted lists. Because of the many documents indexed by such engines and stringent…

Information Retrieval · Computer Science 2022-02-08 Giulio Ermanno Pibiri , Rossano Venturini

High-dimensional sparse modeling via regularization provides a powerful tool for analyzing large-scale data sets and obtaining meaningful, interpretable models. The use of nonconvex penalty functions shows advantage in selecting important…

Methodology · Statistics 2016-05-12 Zemin Zheng , Yingying Fan , Jinchi Lv

Why does the low dimensionality of representations, typically $d\approx 1000$, not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of data points? To answer this question, we study maximal-margin…

Machine Learning · Computer Science 2026-05-25 Kiril Bangachev , Guy Bresler , Jonathan Kogan , Yury Polyanskiy

Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding…

Computation and Language · Computer Science 2016-10-14 Yunchuan Chen , Lili Mou , Yan Xu , Ge Li , Zhi Jin