Recent advances and future trends in information retrieval system: A survey
Mohit Chowdhary, Poonam Chahal
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Models utilized for information retrieval in the first and second phases have been studied. The most recent cutting-edge models, such as term-based, semantic retrieval, and neural approaches are explored. In addition, we look at critical themes connected to these models’ learning processes. This survey provides a complete picture of the area and is relevant to scholars working in the information retrieval domain. This survey comprehensively reviews recent advances and future trends in Information Retrieval Systems (IRS), highlighting the transformative progress and emerging directions in the field. In order to manage and retrieve pertinent information from large and expanding databases, information retrieval, or IR, is essential. This study groups developments into many important domains: natural language processing (NLP), machine learning and deep learning applications, user interaction and personalization, and scalable retrieval strategies. Recent innovations have greatly improved IRS's accuracy, effectiveness, and user experience. Text and multimedia retrieval has been transformed by the incorporation of deep learning, especially through neural networks and transformers, while advances in natural language processing have enhanced semantic comprehension and context awareness. Furthermore, more user-friendly and pertinent search experiences have been made possible by tailored retrieval algorithms that take use of user behaviour and preferences. The study also discusses the difficulties that large data presents with regard to scalability and real-time processing. Lastly, it looks at emerging themes including cross-lingual retrieval, explainable AI, and the moral implications of IR technologies. The purpose of this article is to give practitioners and researchers a comprehensive overview of the state of the field and its future directions in information retrieval systems.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIInformation Retrieval and Search Behavior
Topic Modeling · Recommender Systems and Techniques