Improving Ranking Using Hybrid Custom Embedding Models on Persian Web

Abstract

Ranking plays a crucial role in information retrieval systems, especially in the context of web search engines. This article presents a new ranking approach that utilizes semantic vectors and embedding models to enhance the accuracy of web document ranking, particularly in languages with complex structures like Persian. The article utilizes two real-world datasets, one obtained through web crawling to collect a large-scale Persian web corpus, and the other consisting of real user queries and web documents labeled with a relevancy score. The datasets are used to train embedding models using a combination of static Word2Vec and dynamic BERT algorithms. The proposed hybrid ranking formula incorporates these semantic vectors and presents a novel approach to document ranking called HybridMaxSim. Experiments conducted indicate that the HybridMaxSim formula is effective in enhancing the precision of web document ranking up to 0.87 according to the nDCG criterion.