🤖 AI Summary
To address imprecise similarity computation and low search efficiency in semantic document retrieval, this paper presents a systematic review of swarm intelligence algorithms—including particle swarm optimization, ant colony optimization, and artificial bee colony—applied to semantic retrieval. We propose a dual-mechanism framework termed “cross-modal semantic alignment–dynamic search coordination,” which deeply integrates biologically inspired search strategies with semantic representation learning to enable adaptive alignment and iterative optimization within the query–document semantic space. A taxonomy is constructed to categorize methods by algorithmic principles, semantic fusion paradigms, and application scenarios. Empirical analysis delineates the performance boundaries of state-of-the-art approaches. Our work establishes a novel paradigm and an extensible theoretical foundation for developing efficient, robust intelligent semantic retrieval models.
📝 Abstract
Swarm Intelligence (SI) is gaining a lot of popularity in artificial intelligence, where the natural behavior of animals and insects is observed and translated into computer algorithms called swarm computing to solve real-world problems. Due to their effectiveness, they are applied in solving various computer optimization problems. This survey will review all the latest developments in Searching for documents based on semantic similarity using Swarm Intelligence algorithms and recommend future research directions.