🤖 AI Summary
To address low accuracy and poor efficiency in semantic-similar document retrieval from large-scale text corpora, this paper proposes a collaborative optimization framework integrating evolutionary computation with deep semantic modeling. Methodologically, we innovatively embed genetic algorithms and differential evolution into the deep semantic matching pipeline to jointly optimize both the semantic representation space and the similarity scoring function, while leveraging distributed computing to accelerate training and inference. Our contributions are threefold: (1) We establish the first unified evolutionary computation framework tailored for deep semantic matching; (2) We achieve significant improvements in recall and retrieval speed under complex semantic structures; and (3) We conduct a systematic empirical evaluation of mainstream evolutionary strategies across diverse semantic scenarios, providing theoretical foundations and engineering best practices for interpretable, efficient, and robust intelligent retrieval systems.
📝 Abstract
Identifying similar documents within extensive volumes of data poses a significant challenge. To tackle this issue, researchers have developed a variety of effective distributed computing techniques. With the advancement of computing power and the rise of big data, deep neural networks and evolutionary computing algorithms such as genetic algorithms and differential evolution algorithms have achieved greater success. This survey will explore the most recent advancements in the search for documents based on their semantic text similarity, focusing on genetic and differential evolutionary computing algorithms.