EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using Augmented Small Multimodal Models to Guide Large Language Models for Multimodal Relation Extraction

Wentao He, Hanjie Ma, Shaohua Li, Hui Dong, Haixiang Zhang, Jie Feng

Applied Sciences · 10.11.2023 · 13 (22) · 12208

DOI: 10.3390/app132212208 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 10.11.2023. Verfasst von Wentao He und 5 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal Relation Extraction (MRE) is a core task for constructing Multimodal Knowledge images (MKGs). Most current research is based on fine-tuning small-scale single-modal image and text pre-trained models, but we find that image-text datasets from network media suffer from data scarcity, simple text data, and abstract image information, which requires a lot of external knowledge for supplementation and reasoning. We use Multimodal Relation Data augmentation (MRDA) to address the data scarcity problem in MRE, and propose a Flexible Threshold Loss (FTL) to handle the imbalanced entity pair distribution and long-tailed classes. After obtaining prompt information from the small model as a guide model, we employ a Large Language Model (LLM) as a knowledge engine to acquire common sense and reasoning abilities. Notably, both stages of our framework are flexibly replaceable, with the first stage adapting to multimodal related classification tasks for small models, and the second stage replaceable by more powerful LLMs. Through experiments, our EMRE2llm model framework achieves state-of-the-art performance on the challenging MNRE dataset, reaching an 82.95% F1 score on the test set.

Zitieren

APA

He, W., Ma, H., Li, S., Dong, H., Zhang, H., & Feng, J. (2023). Using Augmented Small Multimodal Models to Guide Large Language Models for Multimodal Relation Extraction. Applied Sciences, 13(22), 12208. https://doi.org/10.3390/app132212208

Vancouver

He W, Ma H, Li S, Dong H, Zhang H, Feng J. Using Augmented Small Multimodal Models to Guide Large Language Models for Multimodal Relation Extraction. Applied Sciences. 2023;13(22):12208. doi:10.3390/app132212208

BibTeX
@article{He2023,
  author = {He, Wentao and Ma, Hanjie and Li, Shaohua and Dong, Hui and Zhang, Haixiang and Feng, Jie},
  title = {Using Augmented Small Multimodal Models to Guide Large Language Models for Multimodal Relation Extraction},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {22},
  pages = {12208},
  doi = {10.3390/app132212208}
}
Kostenlos starten →