Article: A multi modal fusion framework combining CNN-based image recognition and BERT-based NLP for intelligent retrieval and matching of English teaching resources Journal: International Journal of Reasoning-based Intelligent Systems (IJRIS) 2026 Vol.18 No.15 pp.66 - 80 Abstract: Digital English teaching resources combine images and texts, rendering keyword-based retrieval poor in semantic capture. This paper proposes a multimodal retrieval model integrating image recognition and natural language processing to solve this problem. The proposed method uses a five-layer CNN to extract 512-dimensional visual features from 224×224 pixel images and a BERT-based semantic model to generate 768-dimensional text vectors. These features are fused into a 1,024-dimensional unified representation via weighted linear combination (visual weight 0.4, text weight 0.6). On 500 query tasks, the proposed system achieves a precision of 0.91, recall of 0.88, and F1-score of 0.895, with an average response time between 0.63 and 0.78 seconds. Compared to a baseline TF-IDF model (precision 0.72) and a BERT-only model (precision 0.87), the proposed multimodal approach improve precision by 26.4% and 4.6%, respectively. These results demonstrate that multimodal feature representation significantly enhances semantic matching for teaching resources. Inderscience Publishers - linking academia, business and industry through research

Title: A multi modal fusion framework combining CNN-based image recognition and BERT-based NLP for intelligent retrieval and matching of English teaching resources

Authors: Cuimei Li

Addresses: School of International Business, Anhui International Studies University, Hefei 231201, China

Abstract: Digital English teaching resources combine images and texts, rendering keyword-based retrieval poor in semantic capture. This paper proposes a multimodal retrieval model integrating image recognition and natural language processing to solve this problem. The proposed method uses a five-layer CNN to extract 512-dimensional visual features from 224×224 pixel images and a BERT-based semantic model to generate 768-dimensional text vectors. These features are fused into a 1,024-dimensional unified representation via weighted linear combination (visual weight 0.4, text weight 0.6). On 500 query tasks, the proposed system achieves a precision of 0.91, recall of 0.88, and F1-score of 0.895, with an average response time between 0.63 and 0.78 seconds. Compared to a baseline TF-IDF model (precision 0.72) and a BERT-only model (precision 0.87), the proposed multimodal approach improve precision by 26.4% and 4.6%, respectively. These results demonstrate that multimodal feature representation significantly enhances semantic matching for teaching resources.

Keywords: image recognition; natural language processing; intelligent retrieval matching algorithm; English teaching resource management.

DOI: 10.1504/IJRIS.2026.154120

International Journal of Reasoning-based Intelligent Systems, 2026 Vol.18 No.15, pp.66 - 80

Received: 12 Mar 2026
Accepted: 06 May 2026
Published online: 12 Jun 2026 *

Title: A multi modal fusion framework combining CNN-based image recognition and BERT-based NLP for intelligent retrieval and matching of English teaching resources

Keep up-to-date