@inproceedings{al-qurishi-etal-2025-hildoc,
title = "Hildoc: Leveraging {H}ilbert Curve Representation for Accurate and Efficient Document Retrieval",
author = "AL-Qurishi, Muhammad and
Qian, Zhaozhi and
AL-Tam, Faroq and
Souissi, Riad",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.101/",
pages = "1863--1876",
ISBN = "979-8-89176-298-5",
abstract = "Document retrieval is a critical challenge in information retrieval systems, where the goal is to efficiently retrieve relevant documents in response to a given query. Dense retrieval methods, which utilize vector embeddings to represent semantic information, require effective indexing to ensure fast and accurate retrieval. Existing methods, such as MEVI, have attempted to address this by using hierarchical K-Means for clustering, but they often face limitations in computational efficiency and retrieval accuracy. In this paper, we introduce the Hildoc Index, a novel document indexing approach that leverages the Hilbert Curve to map document embeddings onto a one-dimensional space. This innovative representation facilitates efficient clustering using a 1D quantile-based algorithm, ensuring uniform partition sizes and preserving the inherent structure of the data. As a result, Hildoc Index not only reduces training complexity but also enhances retrieval accuracy and speed during inference. Our method can be seamlessly integrated into both dense retrieval systems and hybrid ensemble systems. Through comprehensive experiments on standard benchmarks like MSMARCO Passage and Natural Questions, we demonstrate that the Hildoc Index significantly outperforms the current state-of-the-art MEVI in terms of both retrieval speed and recall. These results underscore the Hildoc Index as a solution for fast and accurate dense document retrieval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-qurishi-etal-2025-hildoc">
<titleInfo>
<title>Hildoc: Leveraging Hilbert Curve Representation for Accurate and Efficient Document Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">AL-Qurishi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaozhi</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faroq</namePart>
<namePart type="family">AL-Tam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riad</namePart>
<namePart type="family">Souissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Document retrieval is a critical challenge in information retrieval systems, where the goal is to efficiently retrieve relevant documents in response to a given query. Dense retrieval methods, which utilize vector embeddings to represent semantic information, require effective indexing to ensure fast and accurate retrieval. Existing methods, such as MEVI, have attempted to address this by using hierarchical K-Means for clustering, but they often face limitations in computational efficiency and retrieval accuracy. In this paper, we introduce the Hildoc Index, a novel document indexing approach that leverages the Hilbert Curve to map document embeddings onto a one-dimensional space. This innovative representation facilitates efficient clustering using a 1D quantile-based algorithm, ensuring uniform partition sizes and preserving the inherent structure of the data. As a result, Hildoc Index not only reduces training complexity but also enhances retrieval accuracy and speed during inference. Our method can be seamlessly integrated into both dense retrieval systems and hybrid ensemble systems. Through comprehensive experiments on standard benchmarks like MSMARCO Passage and Natural Questions, we demonstrate that the Hildoc Index significantly outperforms the current state-of-the-art MEVI in terms of both retrieval speed and recall. These results underscore the Hildoc Index as a solution for fast and accurate dense document retrieval.</abstract>
<identifier type="citekey">al-qurishi-etal-2025-hildoc</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.101/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>1863</start>
<end>1876</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hildoc: Leveraging Hilbert Curve Representation for Accurate and Efficient Document Retrieval
%A AL-Qurishi, Muhammad
%A Qian, Zhaozhi
%A AL-Tam, Faroq
%A Souissi, Riad
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F al-qurishi-etal-2025-hildoc
%X Document retrieval is a critical challenge in information retrieval systems, where the goal is to efficiently retrieve relevant documents in response to a given query. Dense retrieval methods, which utilize vector embeddings to represent semantic information, require effective indexing to ensure fast and accurate retrieval. Existing methods, such as MEVI, have attempted to address this by using hierarchical K-Means for clustering, but they often face limitations in computational efficiency and retrieval accuracy. In this paper, we introduce the Hildoc Index, a novel document indexing approach that leverages the Hilbert Curve to map document embeddings onto a one-dimensional space. This innovative representation facilitates efficient clustering using a 1D quantile-based algorithm, ensuring uniform partition sizes and preserving the inherent structure of the data. As a result, Hildoc Index not only reduces training complexity but also enhances retrieval accuracy and speed during inference. Our method can be seamlessly integrated into both dense retrieval systems and hybrid ensemble systems. Through comprehensive experiments on standard benchmarks like MSMARCO Passage and Natural Questions, we demonstrate that the Hildoc Index significantly outperforms the current state-of-the-art MEVI in terms of both retrieval speed and recall. These results underscore the Hildoc Index as a solution for fast and accurate dense document retrieval.
%U https://aclanthology.org/2025.ijcnlp-long.101/
%P 1863-1876
Markdown (Informal)
[Hildoc: Leveraging Hilbert Curve Representation for Accurate and Efficient Document Retrieval](https://aclanthology.org/2025.ijcnlp-long.101/) (AL-Qurishi et al., IJCNLP-AACL 2025)
ACL
- Muhammad AL-Qurishi, Zhaozhi Qian, Faroq AL-Tam, and Riad Souissi. 2025. Hildoc: Leveraging Hilbert Curve Representation for Accurate and Efficient Document Retrieval. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 1863–1876, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.