Research on Popular Science Image-Text Generation Method Based on Concept Constraint and Semantic Consistency Reranking
Cognitive Strategies in Study · 16.08.2026 · 2 (3) · 1-20
DOI: 10.63808/css.v2i3.427 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cognitive Strategies in Study, online erschienen am 16.08.2026. Verfasst von Yuewen Cao und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
General text-to-image models suffer from key concept missing, image-text semantic deviation and insufficient educational applicability in popular science education scenarios. To address these problems, this paper proposes a popular science image-text generation method based on concept constraint and semantic consistency reranking. Firstly, the method extracts scientific concept sets from input popular science texts and constructs enhanced prompts combined with disciplinary categories and image expression requirements. Secondly, the pre-trained Chinese text-to-image generator IDEA-CCNL /Taiyi-Stable-Diffusion-1B-Chinese-v0.1 is invoked to generate multiple candidate images. Finally, candidate images are reranked and the optimal result is output by comprehensively integrating CLIP image-text similarity, scientific concept coverage and image educational applicability scores. Experiments are conducted on a self-built popular science text-image evaluation dataset to compare the proposed method with conventional diffusion model generation, prompt enhancement and single CLIP reranking methods. The experimental results show that the proposed method can effectively improve image-text consistency and concept expression completeness, and is especially suitable for lightweight application scenarios such as scientific concept explanation, classroom illustration matching and popular science resource generation. The paper further reports exact implementation settings, concept extraction rules, an educational applicability rubric, evaluator calibration, inter-rater agreement, per-discipline results, statistical significance testing, qualitative comparisons and failure cases, thereby improving evaluation transparency and reproducibility.
Zitieren
APA
Cao, Y., Li, X., Lei, C., & Zhang, L. (2026). Research on Popular Science Image-Text Generation Method Based on Concept Constraint and Semantic Consistency Reranking. Cognitive Strategies in Study, 2(3), 1-20. https://doi.org/10.63808/css.v2i3.427
Vancouver
Cao Y, Li X, Lei C, Zhang L. Research on Popular Science Image-Text Generation Method Based on Concept Constraint and Semantic Consistency Reranking. Cognitive Strategies in Study. 2026;2(3):1-20. doi:10.63808/css.v2i3.427
BibTeX
@article{Cao2026,
author = {Cao, Yuewen and Li, Xinyang and Lei, Chunyu and Zhang, Lin},
title = {Research on Popular Science Image-Text Generation Method Based on Concept Constraint and Semantic Consistency Reranking},
journal = {Cognitive Strategies in Study},
year = {2026},
volume = {2},
number = {3},
pages = {1--20},
doi = {10.63808/css.v2i3.427}
}
EUVIMED