paper-with-me

홈 › Papers

Sparse, Dense, and Attentional Representations for Text Retrieval

2020-05-01 · Yi Luan, Jacob Eisenstein, Kristina Toutanova, Michael Collins

Dual encoders perform retrieval by encoding documents and queries into dense lowdimensional vectors, scoring each document by its inner product with the query. We investigate the capacity of this architecture relative to sparse bag-of-words models and attentional neural networks. Using both theoretical and empirical analysis, we establish connections between the encoding dimension, the margin between gold and lower-ranked documents, and the document length, suggesting limitations in the capacity of fixed-length encodings to support precise retrieval of long documents. Building on these insights, we propose a simple neural model that combines the efficiency of dual encoders with some of the expressiveness of more costly attentional architectures, and explore sparse-dense hybrids to capitalize on the precision of sparse retrieval. These models outperform strong alternatives in large-scale retrieval.

📄 PDF Abstract BibTeX arXiv:2005.00181

Code (1)

google-research/language/tree/master/language/multivec 공식 구현 tf

Tasks

Open-Domain Question AnsweringRetrievalText Retrieval

Similar Papers 제목 키워드 기반

Densifying Sparse Representations for Passage Retrieval by Representational Slicing

2021-12-09 · Sheng-Chieh Lin, Jimmy Lin

Learned sparse and dense representations capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust. Prior work combines dense and sparse retrieve…

Passage RetrievalRetrievalText Retrieval

Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrieval

2025-08-22 · Jonghyun Song, Youngjune Lee, Gyu-Hwung Cho, Ilhyeon Song 외 arxiv

Vision-Language Pretrained (VLP) models have achieved impressive performance on multimodal tasks, including text-image retrieval, based on dense representations. Meanwhile, Learned Sparse Retrieval (LSR) has gained tract…

Knowledge DistillationImage Retrieval

Dense Sparse Retrieval: Using Sparse Language Models for Inference Efficient Dense Retrieval

2023-03-31 · Daniel Campos, ChengXiang Zhai

Vector-based retrieval systems have become a common staple for academic and industrial search applications because they provide a simple and scalable way of extending the search to leverage contextual representations for…

RetrievalTriviaQA

The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes

2020-12-28 · ACL 2021 5 · Nils Reimers, Iryna Gurevych

Information Retrieval using dense low-dimensional representations recently became popular and showed out-performance to traditional sparse-representations like BM25. However, no previous work investigated how dense repre…

Information RetrievalRetrieval

Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection

2021-09-22 · Negar Arabzadeh, Xinyi Yan, Charles L. A. Clarke

Over the last few years, contextualized pre-trained transformer models such as BERT have provided substantial improvements on information retrieval tasks. Recent approaches based on pre-trained transformer models such as…

GPUInformation RetrievalRetrieval