Improving Query Understanding and Document Retrieval in Search Engines Using BERT and Large Language Models
Intelligent & Human Futures · 2026
DOI: 10.63808/ihf.v2i1.292 ↗Kurz gefasst
Fachartikel in der Zeitschrift Intelligent & Human Futures, 2026. Verfasst von Bangyi Yang. Die Arbeit wurde bisher 4-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Information retrieval systems are examined from traditional lexical matching to modern neural models that are able to capture the semantic relationship between the query and the documents. A novel framework is proposed by integrating the query understanding component based on the BERT model and the rerank approach guided by the language model, aiming at enhancing the search engine effectiveness. Experiments conducted on the MSMARCO benchmark show significant improvements of 47.0% relative NDCG@10 values compared to the baseline BM25 model and an absolute 15.9% boost over the baseline BERT model. The query understanding model attains an accuracy of 94.3% on the intent classification task while being computationally efficient enough to be put into practice.
Zitieren
APA
Yang, B. (2026). Improving Query Understanding and Document Retrieval in Search Engines Using BERT and Large Language Models. Intelligent & Human Futures. https://doi.org/10.63808/ihf.v2i1.292
Vancouver
Yang B. Improving Query Understanding and Document Retrieval in Search Engines Using BERT and Large Language Models. Intelligent & Human Futures. 2026. doi:10.63808/ihf.v2i1.292
BibTeX
@article{Yang2026,
author = {Yang, Bangyi},
title = {Improving Query Understanding and Document Retrieval in Search Engines Using BERT and Large Language Models},
journal = {Intelligent & Human Futures},
year = {2026},
doi = {10.63808/ihf.v2i1.292}
}
EUVIMED