paper-with-me

Papers

Accurate and Fast Retrieval for Complex Non-metric Data via Neighborhood Graphs

2019-10-08 · Leonid Boytsov, Eric Nyberg

We demonstrate that a graph-based search algorithm-relying on the construction of an approximate neighborhood graph-can directly work with challenging non-metric and/or non-symmetric distances without resorting to metric-space mapping and/or distance symmetrization, which, in turn, lead to substantial performance degradation. Although the straightforward metrization and symmetrization is usually ineffective, we find that constructing an index using a modified, e.g., symmetrized, distance can improve performance. This observation paves a way to a new line of research of designing index-specific graph-construction distance functions.

📄 PDF Abstract BibTeX arXiv:1910.03534

Code (0)

등록된 구현이 없습니다.

Tasks

graph constructionRetrieval

Similar Papers 제목 키워드 기반

Product Quantization Network for Fast Image Retrieval

2018-09-01 · ECCV 2018 9 · Tan Yu, Junsong Yuan, Chen Fang, Hailin Jin

Product quantization has been widely used in fast image retrieval due to its effectiveness of coding high-dimensional visual features. By extending the hard assignment to soft assignment, we make it feasible to incorpora…

Image RetrievalQuantizationRetrievalTriplet

Build Fast and Accurate Lemmatization for Arabic

2017-10-18 · LREC 2018 5 · Hamdy Mubarak

In this paper we describe the complexity of building a lemmatizer for Arabic which has a rich and complex derivational morphology, and we discuss the need for a fast and accurate lammatization to enhance Arabic Informati…

Information RetrievalLemmatizationRetrieval

FastRAG: Retrieval Augmented Generation for Semi-structured Data

2024-11-21 · Amar Abane, Anis Bekri, Abdella Battou, Saddek Bensalem

Efficiently processing and interpreting network data is critical for the operation of increasingly complex networks. Recent advances in Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) techniques have…

ManagementQuestion AnsweringRAGRetrieval+1

RetrievalRouter: Joint Modality and Architecture Selection for Document Retrieval

2026-08-26 · Emre Kuru, Mehmet Onur Keskin, Reza Farahbakhsh, Noel Crespi hf

Document retrieval increasingly supports high-stakes information access in finance, healthcare, and law. Modern retrieval pipelines vary both in modality (text or multimodal) and in retrieval architecture (dense or late-…

Adaptive additive classification-based loss for deep metric learning

2020-06-25 · Istvan Fehervari, Ives Macedo

Recent works have shown that deep metric learning algorithms can benefit from weak supervision from another input modality. This additional modality can be incorporated directly into the popular triplet-based loss functi…

ClassificationGeneral ClassificationMetric LearningRetrieval+1