Saved in:
Bibliographic Details
Main Author: IRE Journals
Format: Recurso digital
Language:
Published: Zenodo 2023
Online Access:https://doi.org/10.5281/zenodo.15128372
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866902236306604032
author IRE Journals
author_facet IRE Journals
contents <p>The exponential growth of digital repositories demands intelligent document retrieval beyond conventional indexing and keyword-based searches. Machine Learning (ML) techniques, particularly deep learning, neural ranking models, and reinforcement learning, enhance retrieval efficiency, scalability, and contextual understanding. This study explores ML- driven methodologies for document classification, ranking, and multimodal retrieval, integrating natural language processing (NLP) and transformer-based architectures. We analyze advancements in enterprise content management, legal document retrieval, and OCR-based processing, highlighting the superior- ity of deep learning over traditional search methods. Despite significant improvements, challenges persist in model scalability, explainability, and real-time retrieval. Future research should focus on optimizing federated learning for privacy-preserving search, enhancing explainable AI, and improving neural indexing for large-scale repositories.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_15128372
institution Zenodo
language
publishDate 2023
publisher Zenodo
record_format zenodo
spellingShingle AI and Machine Learning Approaches for Efficient Document Retrieval
IRE Journals
<p>The exponential growth of digital repositories demands intelligent document retrieval beyond conventional indexing and keyword-based searches. Machine Learning (ML) techniques, particularly deep learning, neural ranking models, and reinforcement learning, enhance retrieval efficiency, scalability, and contextual understanding. This study explores ML- driven methodologies for document classification, ranking, and multimodal retrieval, integrating natural language processing (NLP) and transformer-based architectures. We analyze advancements in enterprise content management, legal document retrieval, and OCR-based processing, highlighting the superior- ity of deep learning over traditional search methods. Despite significant improvements, challenges persist in model scalability, explainability, and real-time retrieval. Future research should focus on optimizing federated learning for privacy-preserving search, enhancing explainable AI, and improving neural indexing for large-scale repositories.</p>
title AI and Machine Learning Approaches for Efficient Document Retrieval
url https://doi.org/10.5281/zenodo.15128372